To see the other types of publications on this topic, follow the link: Forecasting.
Dissertations / Theses on the topic 'Forecasting'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Forecasting.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Warren, Steven W. MATHEMATICAL MODELS WEATHER FORECASTING WEATHER PREDICTIONS MODELS REDUCTION PHYSICS OCEANOGRAPHY POWER REGRESSION ANALYSIS NAVY COMPARISON FORECASTING THESES. "Ensemble forecasting techniques in medium-range forecasting /." Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1993. http://handle.dtic.mil/100.2/ADA267443.
Full textAbstract:
Thesis (M.S. in Meteorology and Physical Oceanography) Naval Postgraduate School, March 1993.<br>Thesis advisor(s): Wendell A. Nuss. "March 1993." Page 66 is missing (which includes Fig. 21 a-b). Bibliography: p. 109. Also available online.
2
Warren, Steven W. "Ensemble forecasting techniques in medium-range forecasting." Thesis, Monterey, California. Naval Postgraduate School, 1993. http://hdl.handle.net/10945/39902.
Full textAbstract:
Approved for public release; distribution is unlimited.<br>A continuing trend in numerical weather prediction (NWP) is the desire for reduced model forecast error. Developments in NWP such as advanced computing power and improved model physics and analysis methods have been successful in lowering error but are potentially limited The regression method of ensemble forecasting is used to further reduce mean forecast error when compared to individual model forecast performances. A statistical regression scheme is utilized to achieve an optimum combination fitting of the National Meteorological Center, the European Centre for Medium-Range Weather Forecasts, and the U.S. Navy Fleet Numerical Oceanography Center forecast models. The performance of the regression model is evaluated for 72-h and 108-h prediction cycles through statistical and subjective comparisons with the individual models and an equally weighted ensemble model at the surface and at 500 hPa. The regression model is shown to produce gains through the reduction of systematic error present in the individual model forecasts...
3
Abdullah, Rozi. "Rainfall forecasting algorithms for real time flood forecasting." Thesis, University of Newcastle Upon Tyne, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.296151.
Full textAbstract:
A fast catchment response usually leads to a shorter lag time, and under these conditions the forecast lead time obtained from a rainfall-runoff model or correlation between upstream and downstream flows may be infeasible for flood warning purposes. Additional lead time can be obtained from short-term quantitative rainfall forecasts that extend the flood warning time and increase the economic viability of a flood forecasting system. For this purpose algorithms which forecasts the quantitative rainfall amounts up to six hours ahead have been developed, based on lumped and distributed approaches. The lumped forecasting algorithm includes the essential features of storm dynamics such as rainband and raincell movements which are represented within the framework of a linear transfer function model. The dynamics of a storm are readily captured by radar data. A space-time rainfall model is used to generate synthetic radar data with known features, e.g. rainband and raincell velocities. This enables the algorithm to be assessed under ideal conditions, as errors are present in observed radar data. The transfer function algorithm can be summarised as follows. The dynamics of the rainbands and raincells are incorporated as inputs into the transfer function model. The algorithm employs simple spatial cross-correlation techniques to estimate the rainband and raincell velocities. The translated rainbands and raincells then form the auxiliary inputs to the transfer function. An optimal predictor based on minimum square error is then derived from the transfer function model, and its parameters are estimated from the auxiliary inputs and observed radar data in real-time using a recursive least squares algorithm. While the transfer-function algorithm forecasts areal rainfalls, a distributed approach which performs rainfall forecasting at a fine spatial resolution (referred to as the advection equation algorithm) is also evaluated in this thesis. The algorithm expresses the space-time rainfall on a Cartesian coordinate system via a partial differential advection equation. A simple explicit finite difference solution scheme is applied to the equation. A comparison of model parameter estimates is undertaken using a square root information filter data processing algorithm, and single-input single-output and multiple-input multiple-output least squares algorithms.
4
Rasmussen, Steven R. "Forecasting 5" /." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1995. http://handle.dtic.mil/100.2/ADA304364.
Full text
5
Jessen, Andreas, and Carina Kellner. "Forecasting Management." Thesis, University of Kalmar, Baltic Business School, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:hik:diva-1868.
Full textAbstract:
<p>In a world that is moving faster and faster, a company’s ability to align to market changes is becoming a major competitive factor. Forecasting enables companies to predict what lies ahead, e.g. trend shifts or market turns, and makes it possible to plan for it. But looking into the future is never an easy task.</p><p>“Prediction is very difficult, especially if it’s about the future.” (Niels Bohr, 1885-1962)</p><p>However, progress in the field of forecasting has shown that it is possible for companies to improve on forecasting practices. This master thesis looks at the sales forecasting practices in MNCs primarily operating in emerging and developing countries. We examine the whole process of sales forecasting, also known as forecasting management, in order to develop a comprehensive model for forecasting in this type of companies. The research is based on a single case study, which is then later generalized into broader conclusions.</p><p>The conclusion of this master thesis is that forecasting is a four-step exercise. The four stages we have identified are: Knowledge creation, knowledge transformation, knowledge use and feedback. In the course of these four stages a company’s sales forecast is developed, changed and used. By understanding how each stage works and what to focus on, companies will be able to improve their forecasting practices.</p>
6
Minkah, Richard. "Forecasting volatility." Thesis, Uppsala University, Department of Mathematics, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-121079.
Full text
7
Mayr, Johannes. "Forecasting Macroeconomic Aggregates." Diss., lmu, 2010. http://nbn-resolving.de/urn:nbn:de:bvb:19-111404.
Full text
8
Noble, Christopher J. "Forecasting vortex filaments." Thesis, University of Canterbury. Physics, 1998. http://hdl.handle.net/10092/8165.
Full textAbstract:
The accuracy of stratospheric forecasts from the United Kingdom Meteorological Office's (UKMO) assimilation system in the Southern Hemisphere (SH) are studied primarily for a period in October 1994 and also February 1995. Conventional root mean square error (RMSE) calculations for different regions show that stratospheric forecasts are a large improvement over persistence in October 1994 (SH winter) even at five days but not so during February 1995 (SH summer). Systematic errors in the temperature and zonal wind fields were found to occur in relation with the stratopause and polar jet respectively. Studies also show that in general the vortex minimum temperature is forecast too cool and the maximum wind in the polar jet is forecast too strong. An advection scheme on specialised parcel location fields is used to study the differences in the meridional component of the wind vector with results indicating the forecast winds are highly consistent with the analysed winds even after five days in most cases. A back-trajectory mapping technique is employed to generate high-resolution maps of isentropic potential vorticity to permit the study of small-scale structure. The overall structure in a total hemisphere field produced from forecast winds is very similar to that from analysed winds even for filamentary structure near the polar vortex. Qualitative comparisons of aircraft measured tracer structure during the Airborne Southern Hemisphere Ozone Experiment (ASHOE) 1994 with structure from the high-resolution potential vorticity maps shows that large-scale features are represented well by the back-trajectory mapping technique with possibly less success for small-scale structure.
9
CHRISTO, ELIANE DA SILVA. "REACTIVE POWER FORECASTING." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2005. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=7622@1.
Full textAbstract:
CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO<br>No novo modelo do Setor Elétrico é essencial desenvolver novas técnicas
que estimem valores futuros, a curto e longo-prazos, das potências ativa e reativa.
Com base nisso, este trabalho tem por objetivo apresentar uma nova técnica de
previsão horária de potência reativa a curto-prazo, por subestação, baseada na
linearidade existente entre as potências ativa e reativa. O modelo proposto,
denominado de Modelo Híbrido de Previsão de Reativo, é dividido em duas
etapas: A primeira etapa é feita uma classificação dos dados através de uma rede
neural não supervisionada Mapas Auto-Organizáveis de Kohonen (SOM); A
segunda etapa, utiliza-se um modelo de defasagem distribuída auto-regressivo
(ADL) com estimação de Mínimos Quadrados Reponderados Iterativamente
(IRLS) acoplado a uma correção para autocorrelação serial dos resíduos - Método
Iterativo de Cochrane-Orcutt. Este Modelo Híbrido tem como variável dependente
a potência reativa, e como variáveis explicativas dados horários de potência ativa
e reativa no instante atual e defasadas no tempo. A previsão de potência reativa a
curto-prazo é dividida em in sample e em out of sample. A previsão out of
sample é aplicada a períodos horários em até um mês à frente. O modelo
proposto é aplicado aos dados de uma concessionária específica de Energia
Elétrica e os resultados são comparados a um modelo de Regressão Dinâmica
convencional e a um modelo de Redes Neurais Artificiais Feedforward de
Múltiplas camadas (MLP) com um algoritmo de retropropagação do erro.<br>The forecasting of reactive and active power is an
important tool in the
monitoring of an Electrical Energy System. The main
purpose of the present work
is the development of a new short-term reactive power
hourly forecast technique,
which can be used at utility or substations levels. The
proposed model, named A
Hybrid Model for Reactive Forecasting, is divided in two
stages. In the first
stage, the active and reactive power data are classified
by an unsupervised neural
network - the Self-Organized Maps of Kohonen (SOM). In the
second stage, a
Autoregressive Distributed Lags Model (ADL) is used with
its parameters
estimated by an Iteratively Reweighted Least Square
(IRLS). It also includes a
correction lag structure for serial autocorrelation of the
residuals as used in the
Cochrane-Orcutt formulation. The short term reactive power
forecasting is
divided in in sample and out of sample. The out of sample
forecast is
applied to hourly periods until one month ahead. The
proposed model is applied to
real data of one substation and the results are compared
with two other
approaches, a conventional Dynamic Regression and a
Feedforward Multi-layer
Perceptron (MLP) Artificial Neural Network model.
10
Binter, Roman. "Applied probabilistic forecasting." Thesis, London School of Economics and Political Science (University of London), 2012. http://etheses.lse.ac.uk/559/.
Full textAbstract:
In any actual forecast, the future evolution of the system is uncertain and the forecasting model is mathematically imperfect. Both, ontic uncertainties in the future (due to true stochasticity) and epistemic uncertainty of the model (reflecting structural imperfections) complicate the construction and evaluation of probabilistic forecast. In almost all nonlinear forecast models, the evolution of uncertainty in time is not tractable analytically and Monte Carlo approaches (”ensemble forecasting”) are widely used. This thesis advances our understanding of the construction of forecast densities from ensembles, the evolution of the resulting probability forecasts and methods of establishing skill (benchmarks). A novel method of partially correcting the model error is introduced and shown to outperform a competitive approach. The properties of Kernel dressing, a method of transforming ensembles into probability density functions, are investigated and the convergence of the approach is illustrated. A connection between forecasting and Information theory is examined by demonstrating that Kernel dressing via minimization of Ignorance implicitly leads to minimization of Kulback-Leibler divergence. The Ignorance score is critically examined in the context of other Information theory measures. The method of Dynamic Climatology is introduced as a new approach to establishing skill (benchmarking). Dynamic Climatology is a new, relatively simple, nearest neighbor based model shown to be of value in benchmarking of global circulation models of the ENSEMBLES project. ENSEMBLES is a project funded by the European Union bringing together all major European weather forecasting institutions in order to develop and test state-of-the-art seasonal weather forecasting models. Via benchmarking the seasonal forecasts of the ENSEMBLES models we demonstrate that Dynamic Climatology can help us better understand the value and forecasting performance of large scale circulation models. Lastly, a new approach to correcting (improving) imperfect model is presented, an idea inspired by [63]. The main idea is based on a two-stage procedure where a second stage ‘corrective’ model iteratively corrects systematic parts of forecasting errors produced by a first stage ‘core’ model. The corrector is of an iterative nature so that at a given time t the core model forecast is corrected and then used as an input into the next iteration of the core model to generate a time t + 1 forecast. Using two nonlinear systems we demonstrate that the iterative corrector is superior to alternative approaches based on direct (non-iterative) forecasts. While the choice of the corrector model class is flexible, we use radial basis functions. Radial basis functions are frequently used in statistical learning and/or surface approximations and involve a number of computational aspects which we discuss in some detail.
11
SESKAUSKIS, ZYGIMANTAS, and ROKAS NARKEVICIUS. "Sales forecasting management." Thesis, Högskolan i Borås, Akademin för textil, teknik och ekonomi, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-10685.
Full textAbstract:
The purpose of this research is to investigate current company business process from sales forecasting perspective and provide potential improvements of how to deal with unstable market demand and increase overall precision of forecasting. The problem which company face is an unstable market demand and not enough precision in sales forecasting process. Therefore the research questions are: How current forecasting process can be improved? What methods, can be implemented in order to increase the precision of forecasting? Study can be described as an action research using an abductive approach supported by combination of quantitative and qualitative analysis practices. In order to achieve high degree of reliability the study was based on verified scientific literature and data collected from the case company while collaborating with company’s COO. Research exposed the current forecasting process of the case company. Different forecasting methods were chosen according to the existing circumstances and analyzed in order to figure out which could be implemented in order to increase forecasting precision and forecasting as a whole. Simple exponential smoothing showed the most promising accuracy results, which were measured by applying MAD, MSE and MAPE measurement techniques. Moreover, trend line analysis was applied as well, as a supplementary method. For the reason that the case company presents new products to the market limited amount of historical data was available. Therefore simple exponential smoothing technique did not show accurate results as desired. However, suggested methods can be applied for testing and learning purposes, supported by currently applied qualitative methods.
12
Pacella, Claudia. "Essays on Forecasting." Doctoral thesis, Universite Libre de Bruxelles, 2020. https://dipot.ulb.ac.be/dspace/bitstream/2013/307579/4/CP_ToC.pdf.
Full textAbstract:
In this thesis I apply modern econometric techniques on macroeconomic time series. Forecasting is here developed along several dimensions in the three chapters. The chapters are in principle self-contained. However, a common element is represented by the business cycle analysis. In the first paper, which primarily deals with the problem of forecasting euro area inflation in the short and medium run, we also compute the country-specific responses of a common business cycle shock. Both chapters 2 and 3 deal predominately with business cycle issues from two different perspectives. The former chapter analyses the business cycle as a dichotomous non-observable variable and addresses the issue of evaluating the euro area business cycle dating formulated by the CEPR committee, while the latter chapter studies the entire distribution of GDP growth.<br>Doctorat en Sciences économiques et de gestion<br>info:eu-repo/semantics/nonPublished
13
Harrington, Robert P. "Forecasting corporate performance." Diss., Virginia Polytechnic Institute and State University, 1985. http://hdl.handle.net/10919/54515.
Full textAbstract:
For the past twenty years, the usefulness of accounting information has been emphasized. In 1966 the American Accounting Association in its State of Basic Accounting Theory asserted that usefulness is the primary purpose of external financial reports. In 1978 the State of Financial Accounting Concepts, No. 1 affirmed the usefulness criterion. "Financial reporting should provide information that is useful to present and potential investors and creditors and other users..."
Information is useful if it facilitates decision making. Moreover, all decisions are future-oriented; they are based on a prognosis of future events. The objective of this research, therefore, is to examine some factors that affect the decision maker's ability to use financial information to make good predictions and thereby good decisions.
There are two major purposes of the study. The first is to gain insight into the amount of increase in prediction accuracy that is expected to be achieved when a model replaces the human decision-maker in the selection of cues. The second major purpose is to examine the information overload phenomenon to provide research evidence to determine the point at which additional information may contaminate prediction accuracy.
The research methodology is based on the lens model developed by Eyon Brunswick in 1952. Multiple linear regression equations are used to capture the participants’ models, and correlation statistics are used to measure prediction accuracy.<br>Ph. D.
14
Fuksa, Michel Carleton University Dissertation Management Studies. "Forecasting exchange rates." Ottawa, 1997.
Find full text
15
Wang, Zheng. "Solar Power Forecasting." Thesis, The University of Sydney, 2019. https://hdl.handle.net/2123/21248.
Full textAbstract:
Solar energy is a promising environmentally-friendly energy source. Yet its variability affects negatively the large-scale integration into the electricity grid and therefore accurate forecasting of the power generated by PV systems is needed. The objective of this thesis is to explore the possibility of using machine learning methods to accurately predict solar power. We first explored the potential of instance-based methods and proposed two new methods: the data source weighted nearest neighbour (DWkNN) and the extended Pattern Sequence Forecasting (PSF) algorithms. DWkNN uses multiple data sources and considers their importance by learning the best weights based on previous data. PSF1 and PSF2 extended the standard PSF algorithm deal with data from multiple related time series. Then, we proposed two clustering-based methods for PV power prediction: direct and pair patterns. We used clustering to partition the days into groups with similar weather characteristics and then created a separate PV power prediction model for each group. The direct clustering groups the days based on their weather profiles, while the pair patterns consider the weather type transition between two consecutive days. We also investigated ensemble methods and proposed static and dynamic ensembles of neural networks. We first proposed three strategies for creating static ensembles based on random example and feature sampling, as well as four strategies for creating dynamic ensembles by adaptively updating the weights of the ensemble members based on past performance. We then explored the use of meta-learning to further improve the performance of the dynamic ensembles. The methods proposed in this thesis can be used by PV plant and electricity market operators for decision making, improving the utilisation of the generated PV power, planning maintenance and also facilitating the large-scale integration of PV power in the electricity grid.
16
Sanchez, Janice Lynn. "Interpersonal affective forecasting." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:6946943f-30fb-48e2-9c73-a44ec69bd2d0.
Full textAbstract:
This thesis investigates individual and interpersonal predictions of future affect and explores their relation to implicit theories of emotion, prediction recall, debiasing, and focalism. Studies 1, 2, and 3 assessed affect predictions to upcoming reasoning tests and academic results, and Studies 4, 5, and 6 concerned predictions for self-identified events. The first study investigated the influence of implicit theories of emotion (ITE; Tamir, John, Srivastava, & Gross, 2007) on impact bias and prediction recall manipulating ITE between participant pairs who predicted and reported their affective reactions to feedback on a test of reasoning skills. Neither impact bias nor recalled predictions were affected by the manipulation. Recalled affect predictions differed from original affect predictions, but were not influenced by experienced affect. Study 2 further investigated the effects of target event timing on impact bias and affect prediction recall. The results showed no differences between individual and interpersonal impact biases across conditions. Again, recalled predictions differed from original predictions, and were not influenced by experienced affect. Study 3 investigated the influence of prior information about impact bias on interpersonal affective forecasting involving real-world exam results. The results demonstrated no differences in predictions due to information, however, significantly less unhappiness was predicted for participants’ friends compared to self-predictions. Study 4 examined the effect of different de-biasing information on affective predictions. The results demonstrated no differences in affective predictions by condition and found that participants’ ITE were not associated to affect predictions. Study 5 examined individual and interpersonal affect predictions using a between-subjects design in place of the within-subjects design. The results demonstrated no differences between the affect predictions made for self and for friends, and ITE were not associated with predictions. Study 6 examined the impact bias in interpersonal affective forecasting and the role of focalism. The results demonstrated distinctions between individual and interpersonal affecting forecasting with individual impact bias for positive reactions for negative events and individual and interpersonal reverse impact bias for calm emotional reactions to positive events. Immune neglect was found not to be associated with predictions. Overall, the studies found evidence for similar individual and interpersonal predictions which are resistant to influence.
17
Ahmed, Shadman. "Phase-Out Demand Forecasting : Predictive modeling on forecasting product life cycle." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-287446.
Full textAbstract:
The phase-out stage in a product life cycle can face unpredictable demand. Accurate forecast of the phase-out demand can help supply chain managers to control the number of obsolete inventories. Consequently, having a positive effect in terms of resources and lower scrap costs. In this thesis, we investigated if data-driven forecasting models could improve the accuracy of forecasting the phase-out stage when compared with domain experts. Since the space of available models is vast, a set of 11 best performing models according to literature were investigated. Furthermore, a thorough model selection based on performance suggested that the following three models were best suited to our dataset: Autoregressive Integrated Moving Average (ARIMA), Support Vector Regression (SVR), and Gaussian Process Regression (GPR). The final results showed that none of the models were able to improve the forecast accuracy overall. However, SVR displayed good performance close to the domain experts’ estimates across 14 unique products through variation of analysis. In addition to the comparative study, this study showed that using less data improved the models’ performances. Only 60% of the training data seemed optimal for ARIMA and GPR, while SVR had a good performance with only 80% of data. We present the results along with further research questions to be explored in this domain.<br>Utfasningen i en produktlivscykel kan kännetecknas vara oförutsägbart. En noggrann prognos av stadiet kan ge värdefull insikt såsom att begränsa antalet utgångna inventeringar och om produktens efterfrågan. Detta kan ge positiv ekonomisk effekt samt spara resurser. I denna studie jämförde vi med domän experter om data drivna prognosmodeller kunde förbättra estimeringen av efterfrågan inom utfasningen i en produktlivscykel. På grund av att tillgängligheten av prognosmodeller är omfattande, ett antal modeller studerades som visat bäst resultat i olika studier. Efter en nogrann urval av 11 olika modeller som visade bäst prestanda, användes följande 3 modeller för den senare delen av studien: Autoregressiv Integrerad Glidande Medelvärde (ARIMA), Stödvektor Regression (SVR) och Gaussisk Process Regression (GPR). Resultat visade att ingen av modellerna kunde generellt förbättra prognoserna, dock visade SVR signifikant liknande prognosfel som planestimeringarna från domän experter för 14 unika produkter. Dessutom visades sig att en minskning av data förbättrade prestandan hos modellerna. Där endast 60% av träningsdatat tycktes vara optimalt för ARIMA och GPR medan SVR med 80%. Vi presenterar resultaten ihop med ytterligare frågor som undersöktes inom detta område.
18
Yenilmez-Dramali, Demet. "Moderating effect of forecasting methods between forecasting criteria and export sales forecasting effectiveness : an empirical model for UK organizations." Thesis, Kingston University, 2013. http://eprints.kingston.ac.uk/26591/.
Full textAbstract:
Over the last three decades important advances have been made in developing sales forecasting methods that more accurately reflect market place conditions. However, surveys of sales forecasting practice continue to report only marginal gains in sales forecasting effectiveness. This gap between theory and practice has been identified as a significant issue for sales forecasting research. The literature suggests that this gap should be addressed by examining new factors in sales forecasting. Accuracy, bias, timeliness, cost and environmental turbulence are the most studied forecasting criteria in sales forecasting effectiveness. There are some literatures which address how these factors are affected by the forecast methods the firm uses. Empirical evidence on such a role of the forecasting method is lacking, and existing literature does not take into account whether forecasting criteria's influence on export sales forecasting effectiveness vary depending on the forecasting methods used by the firm. This is the first research gap identified during the literature review. Furthermore, the role of export sales forecasting. effectiveness on export market performance have received only limited attention to date. Linking the forecasting effectiveness to the business performance was reported to be critical in evaluating and improving the firm's sales forecasting capability and sales forecasting climate. However, empirical evidence of this linkage is missing and this is the second gap this study addresses. A conceptual model is proposed and multivariate analysis technique is used to investigate the relationship between dependent (forecasting effectiveness and export performance) and independent variables (forecasting criteria, forecasting methods, managerial characteristics, organizational characteristics and export market orientation). Our finding revealed the impact of bias, timeliness and cost on forecasting effectiveness varies depending on the forecasting methods used by the firm. But no moderating impact of forecasting methods has been found for accuracy and environmental turbulence. Moreover, this study reported the linkage between forecasting effectiveness and export performance when composite forecasting method is used. Identifying the relative importance of all the factors (i.e. accuracy, bias, cost, timeliness, forecasting methods, etc) it becomes possible to set priorities directly reflecting managerial preferences for different forecast criteria. If implementation of such priorities is seen to contradict principles of good forecasting practice, action can be taken to inform managers of the potential negative consequences.
19
Bruno, Jack H. "Evaluating the Weather Research and Forecasting Model Fidelity for Forecasting Lake Breezes." Ohio University Honors Tutorial College / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ouhonors1556189524538244.
Full text
20
Vera, Barberán José María. "Adding external factors in Time Series Forecasting : Case study: Ethereum price forecasting." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-289187.
Full textAbstract:
The main thrust of time-series forecasting models in recent years has gone in the direction of pattern-based learning, in which the input variable for the models is a vector of past observations of the variable itself to predict. The most used models based on this traditional pattern-based approach are the autoregressive integrated moving average model (ARIMA) and long short-term memory neural networks (LSTM). The main drawback of the mentioned approaches is their inability to react when the underlying relationships in the data change resulting in a degrading predictive performance of the models. In order to solve this problem, various studies seek to incorporate external factors into the models treating the system as a black box using a machine learning approach which generates complex models that require a large amount of data for their training and have little interpretability. In this thesis, three different algorithms have been proposed to incorporate additional external factors into these pattern-based models, obtaining a good balance between forecast accuracy and model interpretability. After applying these algorithms in a study case of Ethereum price time-series forecasting, it is shown that the prediction error can be efficiently reduced by taking into account these influential external factors compared to traditional approaches while maintaining full interpretability of the model.<br>Huvudinstrumentet för prognosmodeller för tidsserier de senaste åren har gått i riktning mot mönsterbaserat lärande, där ingångsvariablerna för modellerna är en vektor av tidigare observationer för variabeln som ska förutsägas. De mest använda modellerna baserade på detta traditionella mönsterbaserade tillvägagångssätt är auto-regressiv integrerad rörlig genomsnittsmodell (ARIMA) och långa kortvariga neurala nätverk (LSTM). Den huvudsakliga nackdelen med de nämnda tillvägagångssätten är att de inte kan reagera när de underliggande förhållandena i data förändras vilket resulterar i en försämrad prediktiv prestanda för modellerna. För att lösa detta problem försöker olika studier integrera externa faktorer i modellerna som behandlar systemet som en svart låda med en maskininlärningsmetod som genererar komplexa modeller som kräver en stor mängd data för deras inlärning och har liten förklarande kapacitet. I denna uppsatsen har tre olika algoritmer föreslagits för att införliva ytterligare externa faktorer i dessa mönsterbaserade modeller, vilket ger en bra balans mellan prognosnoggrannhet och modelltolkbarhet. Efter att ha använt dessa algoritmer i ett studiefall av prognoser för Ethereums pristidsserier, visas det att förutsägelsefelet effektivt kan minskas genom att ta hänsyn till dessa inflytelserika externa faktorer jämfört med traditionella tillvägagångssätt med bibehållen full tolkbarhet av modellen.
21
Lindström, Markus. "Forecasting day-ahead electricity prices in Sweden : Has the forecasting accuracy decreased?" Thesis, Umeå universitet, Nationalekonomi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-184649.
Full textAbstract:
Sweden is currently transitioning towards having 100% electricity generation from renewable energy sources by 2040. To reach this goal, Sweden will ramp up the generation from wind power while simultaneously phasing out nuclear power. Replacing nuclear power with an intermittent production source such as wind power has been proven to increase the variability of electricity prices. The purpose of this study has been to investigate if the increasing electricity generation through wind power in Sweden has decreased the accuracy of price forecasts provided by ARIMA models. Using an automated algorithm in R, optimal ARIMA models were chosen to forecast on-peak and off-peak hours for both winter and summer periods in 2015. These forecasts were then compared to forecasts provided by ARIMA models calibrated on data from 2020. The results from the empirical analysis showed that the overall forecast errors are twice as large for the 2020 forecasts indicating that increasing electricity generation from wind power has decreased the forecasting accuracy of price-only statistical models.
22
Carabotta, Laura. "Fiscal Forecasting in Italy." Doctoral thesis, Universitat de Barcelona, 2015. http://hdl.handle.net/10803/301770.
Full textAbstract:
The thesis “Fiscal forecasting in Italy” is comprised of three main chapters in which is analyzed, from an empirical point of view, several issues related to public finance forecasts, with an application to Italy.
Chapter II, “Accuracy of fiscal forecasts in Italy” is focused on one of the most important aspects of the new Treaty: it requires that the decisions and recommendations taken by the European Commission are no longer be based on outcomes but on forecasts.
In this chapter, I evaluate whether fiscal forecasts for Italy are accurate and econometrically efficient. I focus on a large number of deficit forecasts for Italy that come from a variety of sources, including both public and private agencies as well as Italian and international institutions. I analyse the extent of the discrepancies between the yearly released deficit on GDP and its forecast in Italy from 1/1992 to 12/2011. I conduct two types of analysis. In the quantitative analysis, I carry out different accuracy tests to detect which organization is the best forecaster and in what part of the year better results are published. I also compare forecasters’ performance against a naïve benchmark model, which provides a minimum level of accuracy. In the qualitative analysis, I consider the quality of the forecasts and I test efficiency, unbiasedness and serial correlations. I conclude that all fiscal forecasters for Italy provide unbiased and inefficient forecasts. In general, forecast errors do not persist in a regular way. The most relevant result of this analysis is that private forecasters are frequently more accurate than national and international ones.
In Chapter III, “Combine to compete: improving fiscal forecast accuracy over time”, take advantage of the information contained in all individual budget forecasts analysed in the previous chapter to improve their accuracy. I do this by projecting combined forecasts through pooling the judgment and expertise of the forecasters. Following this idea of improving the forecasting accuracy, I apply a variety of combination techniques, both simple and advanced, which account for past forecasting performance, to compute a combined forecast. I look at a same dataset which is analysed in the previous Chapter. My main finding is that different combinations of budget forecasts often result in more accurate forecasts than individual models. This is particularly the case for a weighted forecast combination and Rbest that value the forecasts that have been more accurate in recent periods. Standard tests of forecasting accuracy show that even one year ahead, some of the pooled forecasts significantly outperform a naïve model. I use recently developed fluctuation tests to check forecasting accuracy over time I find that the weighted forecast combinations outperforms other predictors overall years. Its improvement in accuracy is statistically significant when compared to a naïve model.
Chapter IV, “Nowcasting public finance in Italy,” moves from the idea of forecast and combination of annual data to the most recent idea of nowcasting fiscal variables. The reason is to give policy makers the capacity for dynamic monitoring of the public budget’s cash flow. This monthly analysis exploits the information at higher frequencies before the official figure becomes available. The approach that I use consists of using different nowcasting techniques that are well known in the literature. In particular, I propose a set of models that are parsimonious and suitable for real-time monitoring of the fiscal deficit. I conclude that the linear regression models outperform the other techniques used. The introduction of public finance and economic confidence variables and Google trends results in performance gains when compared with the VAR, the time series and autoregressive models.
23
Tagliabracci, Alex. "Essays on macroeconomic forecasting." Doctoral thesis, Universitat Autònoma de Barcelona, 2018. http://hdl.handle.net/10803/665202.
Full textAbstract:
Esta tesis es una colección de tres ensayos empíricos con un enfoque en la previsión. El primer
capítulo se centra en una importante tarea de política como previsión de la inflación. El trabajo
tiene como objetivo investigar como la dinámica del ciclo económico puede afectar la distribución de
las previsiones de inflación. El segundo capítulo considera dos modelos econométricos utilizados en
la literatura de predicción inmediata y propone una comparación con una aplicación al PIB italiano.
El último capítulo se centra en la previsión de los efectos de las emisiones de datos macroeconómicos
sobre los tipos de cambio.
El primer capítulo estudia como el ciclo económico afecta la distribución condicional de las previsiones
de inflación de la zona del euro. Utilizando un enfoque de regresión de cuantiles, estimo
la distribución condicional de la inflación para mostrar su evolución a lo largo del tiempo, lo que
permite asimetrías entre cuantiles. Documentamos la evidencia de los riesgos a la baja de la inflación
que varían en relación con la evolución del estado de la economía, mientras que el riesgo alcista se
mantiene relativamente estable en el tiempo. También encuentro que esta evidencia caracteriza parcialmente
la distribución correspondiente derivada de la Encuesta de pronosticadores profesionales
del BCE.
El segundo capítulo propone dos modelos econométricos multivariados que consideran dos características
importantes en la literatura de predicción inmediata, como datos oportunos y de alta
frecuencia, para predecir el PIB italiano, a saber, un modelo de factor dinámico y un VAR bayesiano
de frecuencia mixta. Un ejercicio pseudo fuera de muestra demonstra tres resultados principales:
(i) ambos modelos superan considerablemente a un estándar de referencia univariante estándar; (ii)
el modelo de factor dinámico resulta ser más confiable al final del período de pronóstico mientras
que el BVAR de frecuencia mixta parece superior con un conjunto de información incompleto; (iii)
la superioridad del pronóstico general del modelo de factor dinámico se debe principalmente a su
capacidad para captar la gravedad de los episodios de recesión.
Finalmente, el tercer capítulo, escrito conjuntamente con Luca Brugnolini y Antonello D’Agostino,
investiga la posible predecibilidad de las sorpresas macroeconómicas y sus efectos sobre los tipos de
cambio. En particular, analizamos dos de los lanzamientos de datos más importantes que afectan
el mercado financiero de EE. UU., Es decir, el cambio en el nivel de empleo nómina no agrícola
(NFP) y el índice de manufactura publicado por el Instituto de Gerencia de Abastecimiento (ISM).
Examinamos el componente inesperado de estos dos, medido por la desviación de la publicación real
del Consenso de Bloomberg. Lo etiquetamos como la sorpresa del mercado e investigamos si su
estructura es parcialmente predecible y en qué casos. En segundo lugar, utilizamos datos de alta
frecuencia en el eurodólar como laboratorio para estudiar el efecto de estas sorpresas. Mostramos
en un marco de regresión que, aunque el ajuste dentro de la muestra es suficientemente bueno, el
rendimiento se deteriora en un entorno fuera de muestra porque un modelo ingenuo difícilmente puede
superarse en una ventana de sesenta minutos después del lanzamiento. Para terminar, demostramos
que bajo ciertas circunstancias existe una estructura que puede ser explotada y brindamos un marco
para aprovecharla.<br>This thesis is a collection of three empirical essays with a focus on forecasting. The first chapter
focuses on an important policy task as forecasting inflation. The work aims to investigate how the
dynamics of the business cycle may impact the distribution of inflation forecasts. The second chapter
considers two econometric models used in the nowcasting literature and propose a comparison with
an application to the Italian GDP. The last chapter is centered around forecasting the effects of
macroeconomic data releases on the exchange rates.
The first chapter studies how the business cycle affects the conditional distribution of euro area
inflation forecasts. Using a quantile regression approach, I estimate the conditional distribution of
inflation to show its evolution over time allowing for asymmetries across quantiles. I document the
evidence of downside risks to inflation which vary in relation to developments of the state of the economy
while the upside risk remains relatively stable over time. I also find that this evidence partially
characterizes the corresponding distribution derived from ECB Survey of Professional Forecasters.
The second chapter proposes two multivarite econometric models that consider two important
characteristics in the nowcasting literature, as timely and high frequency data, to predict Italian
GDP, namely a dynamic factor model and a mixed-frequency Bayesian VAR. A pseudo out-of-sample
exercise shows three main results: (i) both models considerably outperform a standard univariate
benchmark; (ii) the dynamic factor model turns out to be more reliable at the end of the forecasting
period while the mixed-frequency BVAR appears superior with an incomplete information set; (iii)
the overall forecasting superiority of the dynamic factor model is mainly driven by its ability in
capturing the severity of recession episodes.
Finally, the third chapter, jointly written with Luca Brugnolini and Antonello D’Agostino, investigates
the possible predictability of macroeconomic surprises and their effects on the exchange rates.
In particular, we analyze two of the most important data releases that impact the US financial market,
namely the change in the level of non-farm payroll employment (NFP) and the manufacturing
index published by the Institute for Supply Management (ISM). We examine the unexpected component
of these two, as measured by the deviation of the actual release from the Bloomberg Consensus.
We label it as the market surprise, and we investigate whether its structure is partially predictable
and in which cases. Secondly, we use high-frequency data on the eurodollar as a laboratory to study
the effect of these surprises. We show in a regression framework that although the in-sample fit is
sufficiently good, the performance deteriorates in an out-of-sample setting because a naive model
can hardly be beaten in a sixty-minute window after the release. Finally, we demonstrate that under
certain circumstances there is some structure that can be exploited and we provide a framework to
take advantages of it.
24
Odendahl, Florens. "Essays in economic forecasting." Doctoral thesis, Universitat Pompeu Fabra, 2018. http://hdl.handle.net/10803/664016.
Full textAbstract:
This thesis consists of three chapters on forecasting techniques in economics. In chapter 1, I use copulas to estimate multivariate density forecasts based on univariate densities from survey data. Survey-based predictions are often competitive to time series models in their forecasting performance but have a univariate focus and my estimation strategy exploits the information in the surveys’ marginal densities. I subsequently demonstrate the importance of the multivariate aspect for forecasters. In chapter 2, we propose novel tests for forecast rationality, which are robust under the presence of Markov switching. Existing tests focus on constant out-of-sample performances or use non-parametric techniques; consequently, they may lack power against the alternative of discrete switches. Investigating the Blue Chip Fi-nancial Forecasts, we find evidence against forecast unbiasedness during periods of monetary easing. Chapter 3 provides an empirical investigation of the real-time forecasting performance of quantile regressions for predicting diferent vintages of real US GDP growth. My results indicate that quantile regressions are competitive to current benchmark models and that the insample estimation strategy matters for the performance concerning difrent data vintages.<br>Esta tesis consta de tres capítulos sobre métodos predictivos en economía. El primer capítulo propone el uso de cópulas para la elaboración de previsiones de distribuciones multivariantes utilizando datos de encuestas sobre distribuciones univariantes. Las previsiones basadas en sondeos son, a menudo, equiparables a las obtenidas por modelos de series temporales, pero sólo hay datos disponibles para distribuciones univariantes. La estrategia de estimación propuesta utiliza la información de las distribuciones univariantes de los sondeos. Posteriormente queda demostrada la importancia de la perspectiva multivariante en la elaboración de previsiones. El segundo capítulo propone nuevos tests para evaluar la racionalidad de las previsiones, los cuales, resultan sólidos bajo la presencia de Markov switching. En comparación, los tests existentes se centran en probar la prueba entera o usan técnicas no-paramétricas y tienen menos poder contra la alternativa de cambios discretos. Mediante la investigación empírica de la racionalidad del las previsiones del Blue Chip Financial Forecasts, se encuentra evidencia a favor de la hipótesis de un sesgo con Markov switching durante los periodos de relajación monetaria. El tercer capítulo es una investigación empírica de la eficacia del modelo de regresión de cuantiles para prever en tiempo real el crecimiento del PIB estadounidense. Los resultados obtenidos indican que dicho modelo es comparable a los modelos de referencia actuales y que la estrategia de estimación aplicada con diferentes muestras de datos influye los resultados.
25
Stordahl, Kjell. "Long-term telecommunication forecasting." Doctoral thesis, Norwegian University of Science and Technology, Department of Telematics, 2006. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-948.
Full textAbstract:
<p>The key word for the thesis is long-term demand forecasting which have been applied on telecommunications and especially on broadband accesses and traffic.</p><p>The objective with the thesis has been to structure and present work on long-term broadband forecasting, to evaluate the forecasting results and to extract the learning. Each main chapter ends with a section called experiences and conclusions.</p><p>The thesis is organized in seven main parts.</p><p>The first part addresses application of the Delphi technique for long term forecasting broadband accesses. Three Delphi surveys, which have been conducted during a long period, have been evaluated. All three Delphi surveys have used similar procedures in carrying out the survey, except that two of the Delphi surveys were postal surveys, while one was carried out on site. The applied procedure is evaluated based on an important reference article on Delphi surveys and also based on the long-term forecasting results. The Delphi surveys are not very often used. Hence, the description of the way to conduct the surveys and the experiences and also the evaluations of the results are given specific attention in the thesis.</p><p>The second part of the thesis has the title “Long-term broadband technology forecasting”. Results from three papers are presented and evaluated. The papers show the evolution of the forecasting modelling. The first forecasts for the broadband evolution in Western Europe were made before broadband was introduced in the residential market in Western Europe. The long-term forecasts were developed based on Logistic models. The modelling also includes substitution effects between broadband technologies. Experiences have shown that technological knowledge and techno-economic evaluations are crucial for making long-term broadband forecasts. Some attention is also put on available broadband accesses statistics and an approach to separate aggregated broadband statistics to access statistics for the business market and for the residential market.</p><p>“Long-term forecasting models for cost components and technologies” is the third part in the thesis. To be able to evaluate broadband technologies, techno-economic calculations of the “economic” value of the relevant broadband technologies are very important. The extended learning curve model invented by Borgar T Olsen and Kjell Stordahl is presented. The model is much more powerful than the simple exponential learning curve. The extended learning curve makes long-term forecasts of component costs and has the ability to be used directly on technoeconomic calculations, as opposed to the traditional learning curve model, which does not predict the cost as a function of time. In addition the extended learning curve model has interpretable parameters. It is shown that the model may utilize a priori information in cases where too few observations are available.</p><p>The fourth part addresses long-term traffic forecasting. Three papers are enclosed. The chapter starts with a short overview of relevant forecasting models. Then attention is paid to forecasting and network planning. A comprehensive overview of the field is given together with numerous references in the enclosed paper “Forecasting – an important factor for network planning”. Longterm forecasts for the core network is analyzed and discussed. Also some figures for the total broadband traffic evolution in the Norwegian core network is presented. </p><p>The last paper described in the chapter shows how long-term traffic forecasts on aggregated level can be used for traffic matrix forecasting by using the extended weighted least square method. The chapter ends by listing several important drivers for new and enhanced broadband traffic that are important in traffic forecasting models.</p><br>Paper I, III, IV, V, VI, VII and XIII copyright Telenor R&I
26
AJMAL, KHAN, and MAHMOOD HASHMI TAHIR. "Daily Calls Volume Forecasting." Thesis, Högskolan Dalarna, Statistik, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:du-4852.
Full textAbstract:
A massive amount has been written about forecasting but few articles are written about the development of time series models of call volumes for emergency services. In this study, we use different techniques for forecasting and make the comparison of the techniques for the call volume of the emergency service Rescue 1122 Lahore, Pakistan. For the purpose of this study data is taken from emergency calls of Rescue 1122 from 1st January 2008 to 31 December 2009 and 731 observations are used. Our goal is to develop a simple model that could be used for forecasting the daily call volume. Two different approaches are used for forecasting the daily call volume Box and Jenkins (ARIMA) methodology and Smoothing methodology. We generate the models for forecasting of call volume and present a comparison of the two different techniques.
27
Assaf, Hamed. "Real-time flow forecasting." Thesis, University of British Columbia, 1991. http://hdl.handle.net/2429/30815.
Full textAbstract:
The main objective of this research is to develop techniques for updating deterministic river flow forecasts using feedback of real-time (on-line) flow and snowpack data. To meet this objective, previous updating methods have been reviewed and evaluated and typical error patterns in flow forecasts have been analyzed using standard techniques. In addition, a new criterion based on the coefficient of determination and coefficient of efficiency has been introduced to evaluate systematic errors in flow forecasts. Moreover, lagged linear regression has been suggested as a method for detecting and estimating timing errors.
Arising from this initial work, two different updating procedures have been developed. Further work has shown that these two independent procedures can be usefully combined, leading to yet further improvement of forecast. Arising from these methods, two other additional approaches have been formulated, one for correcting timing errors and one for updating snowpack estimation parameters from flow measurements.
The first of the updating methods consists of a flow updating model which was developed
to update the flow forecasts of the UBC watershed model using the most recent flow measurement. The updating process is achieved using the Kalman filter technique. The performance of the updating model is mainly controlled by the relative values of two parameters of the Kalman filter technique: the measurement variance and the state variance. It is found that the measurement variance is best selected as the square of a percentage of the flow. The updating model has been applied on the Illecillewaet river basin in British Columbia. A significant improvement in flow forecasts has been observed.
The second method has been developed to update parameters of an energy budget
snowpack model using on-line snowpack measurements. The updating procedure is based on calculating the value of a snowpack parameter that yields a perfect correspondence between measured and calculated snowpacks. The updated value is then used in the snowpack model to enhance its future forecasts with feedback from previous snowpack measurements. The snowmelts generated by the updated snowpack model are then routed to produce flow forecasts. Applying this model on the snowpack measured at Mt. Fidelity in the upper Columbia River Basin in British Columbia showed that both the snowpack forecasts and the flow forecasts generated from these updated snowpack forecasts were greatly improved.
Because the above two updating methods operate independently, they can be applied in combination whenever an appropriate measurement is available. The combined use of these two methods to data from the Illecillewaet river basin showed an additional improvement in flow forecasts.
As a further development, the snowpack estimation model has been adapted so that a Kalman filter approach can be used to update snowpack estimation parameters from flow measurements.
It is finally concluded that flow forecast updating requires the application of several methods, rather than one simple approach, because errors arise from various sources. In addition, updating procedures may prove useful in achieving a better calibration for watershed models.<br>Applied Science, Faculty of<br>Civil Engineering, Department of<br>Graduate
28
Yetman, James Arthur. "Essays in macroeconomic forecasting." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp02/NQ35986.pdf.
Full text
29
Kambouroudis, Dimos S. "Essays on volatility forecasting." Thesis, University of St Andrews, 2012. http://hdl.handle.net/10023/3191.
Full textAbstract:
Stock market volatility has been an important subject in the finance literature for which now an enormous body of research exists. Volatility modelling and forecasting have been in the epicentre of this line of research and although more than a few models have been proposed and key parameters on improving volatility forecasts have been considered, finance research has still to reach a consensus on this topic. This thesis enters the ongoing debate by carrying out empirical investigations by comparing models from the current pool of models as well as exploring and proposing the use of further key parameters in improving the accuracy of volatility modelling and forecasting. The importance of accurately forecasting volatility is paramount for the functioning of the economy and everyone involved in finance activities. For governments, the banking system, institutional and individual investors, researchers and academics, knowledge, understanding and the ability to forecast and proxy volatility accurately is a determining factor for making sound economic decisions. Four are the main contributions of this thesis. First, the findings of a volatility forecasting model comparison reveal that the GARCH genre of models are superior compared to the more ‘simple' models and models preferred by practitioners. Second, with the use of backward recursion forecasts we identify the appropriate in-sample length for producing accurate volatility forecasts, a parameter considered for the first time in the finance literature. Third, further model comparisons are conducted within a Value-at-Risk setting between the RiskMetrics model preferred by practitioners, and the more complex GARCH type models, arriving to the conclusion that GARCH type models are dominant. Finally, two further parameters, the Volatility Index (VIX) and Trading Volume, are considered and their contribution is assessed in the modelling and forecasting process of a selection of GARCH type models. We discover that although accuracy is improved upon, GARCH type forecasts are still superior.
30
Maissi, Esther. "Dysphoria and affective forecasting." Thesis, University of London, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.542384.
Full text
31
Richardson, Ross Elliot. "Forecasting with Agent Games." Thesis, Imperial College London, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.516973.
Full text
32
Fischer, Ulrike. "Forecasting in Database Systems." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2014. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-133281.
Full textAbstract:
Time series forecasting is a fundamental prerequisite for decision-making processes and crucial in a number of domains such as production planning and energy load balancing. In the past, forecasting was often performed by statistical experts in dedicated software environments outside of current database systems. However, forecasts are increasingly required by non-expert users or have to be computed fully automatically without any human intervention. Furthermore, we can observe an ever increasing data volume and the need for accurate and timely forecasts over large multi-dimensional data sets. As most data subject to analysis is stored in database management systems, a rising trend addresses the integration of forecasting inside a DBMS. Yet, many existing approaches follow a black-box style and try to keep changes to the database system as minimal as possible. While such approaches are more general and easier to realize, they miss significant opportunities for improved performance and usability.
In this thesis, we introduce a novel approach that seamlessly integrates time series forecasting into a traditional database management system. In contrast to flash-back queries that allow a view on the data in the past, we have developed a Flash-Forward Database System (F2DB) that provides a view on the data in the future. It supports a new query type - a forecast query - that enables forecasting of time series data and is automatically and transparently processed by the core engine of an existing DBMS. We discuss necessary extensions to the parser, optimizer, and executor of a traditional DBMS. We furthermore introduce various optimization techniques for three different types of forecast queries: ad-hoc queries, recurring queries, and continuous queries. First, we ease the expensive model creation step of ad-hoc forecast queries by reducing the amount of processed data with traditional sampling techniques. Second, we decrease the runtime of recurring forecast queries by materializing models in a specialized index structure. However, a large number of time series as well as high model creation and maintenance costs require a careful selection of such models. Therefore, we propose a model configuration advisor that determines a set of forecast models for a given query workload and multi-dimensional data set. Finally, we extend forecast queries with continuous aspects allowing an application to register a query once at our system. As new time series values arrive, we send notifications to the application based on predefined time and accuracy constraints. All of our optimization approaches intend to increase the efficiency of forecast queries while ensuring high forecast accuracy.
33
Martin, C. A. "International tourism demand forecasting." Thesis, University of Bradford, 1987. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.379816.
Full text
34
Quintana, José Mario. "Multivariate Bayesian forecasting models." Thesis, University of Warwick, 1987. http://wrap.warwick.ac.uk/34805/.
Full textAbstract:
This thesis concerns theoretical and practical Bayesian modelling of multivariate time series. Our main goal is to intruduce useful, flexible and tractable multivariate forecasting models and provide the necessary theory for their practical implementation. After a brief review of the dynamic linear model we formulate a new matrix-v-ariate generalization in which a significant part of the variance-covariance structure is unknown. And a new general algorithm, based on the sweep operator is provided for its recursive implementation. This enables important advances to be made in long-standing problems related with the specification of the variances. We address the problem of plug-in estimation and apply our results in the context of dynamic linear models. We extend our matrix-variate model by considering the unknown part of the variance-covariance structure to be dynamic. Furthermore, we formulate the dynamic recursive model which is a general counterpart of fully recursive econometric models. The latter part of the dissertation is devoted to modelling aspects. The usefulness of the methods proposed is illustrated with several examples involving real and simulated data.
35
Valente, Giorgio. "Essays in financial forecasting." Thesis, University of Warwick, 2003. http://wrap.warwick.ac.uk/4055/.
Full textAbstract:
Forecasting is central to economic and financial decision-making. Government institutions and agents in the private sector often base their decisions on forecasts of financial and economic variables. Forecasting has therefore been a primary concern for practitioners and financial econometricians alike, and the relevant literature has witnessed a renaissance in recent years. This thesis contributes to this literature by investigating three topical issues related to financial and economic forecasting. The first chapter finds its rationale in the large literature suggesting that standard exchange rate models cannot outperform a random walk forecast and that the forward rate is not an optimal predictor of the spot rate. However, there is some evidence that the term structure of forward premia contains valuable information for forecasting future spot exchange rates and that exchange rate dynamics display nonlinearities. This chapter proposes a term-structure forecasting model of exchange rates based on a regime-switching vector equilibrium correction model which is novel in this context. Our model significantly outperforms both a random walk and, to a lesser extent, a linear term-structure vector equilibrium correction model for four major dollar exchange rates across a range of horizons. The second chapter proposes a vector equilibrium correction model of stock returns that exploits the information in the futures market, while also allowing for regime-switching behavior and international spillovers across stock market indices. Using data for three major stock market indices since 1989, we find that: (i) in sample, the model outperforms several alternative models on the basis of standard statistical criteria; (ii) in out-of-sample forecasting, the model does not produce significant gains in terms of point forecasts relative to more parsimonious alternative specifications, but it does so both in terms of market timing ability and in density forecasting performance. The importance of these gains is illustrated with a simple application to a risk management problem. The third chapter re-examines a major puzzle in international finance that is the inability of exchange rate models based on monetary fundamentals to produce better out-of-sample forecasts of the nominal exchange rate than a naive random walk. While prior research has generally evaluated exchange rate forecasts using conventional statistical measures of forecast accuracy, this chapter investigates whether there is any economic value to the predictive power of monetary fundamentals for the exchange rate. We estimate, using a framework that allows for parameter uncertainty, the economic and utility gains to an investor who manages her portfolio based on exchange rate forecasts from a monetary fundamentals model. In contrast to much previous research, we find that the economic value of the exchange rate forecasts implied by monetary fundamentals can be substantially greater than the economic value of forecasts obtained using a random walk across a range of horizons. In sum this thesis adds to the relevant literature on forecasting financial variables by providing insights and evidence to researchers and indicating potential avenues for futures research.
36
McVean, Ross Iolo Kester. "Forecasting pea aphid outbreaks." Thesis, University of East Anglia, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.389386.
Full text
37
BERTOLOTO, RODRIGO FERREIRA. "FORECASTING TANKER FREIGHT RATE." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2018. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=35800@1.
Full textAbstract:
O transporte marítimo de petróleo e derivados é componente fundamental da cadeia de suprimento da indústria do petróleo, integrando fornecedores e clientes localizados em regiões geográficas distintas. Neste contexto, os valores de fretes praticados possuem grande impacto no comércio internacional destes bens. O objetivo deste trabalho é verificar o desempenho de modelos de Regressão Dinâmica em previsões de frete marítimo de curto prazo do mercado spot de uma rota de exportação de petróleo do oeste da África para a China, comparar a capacidade preditiva do modelo com métodos tradicionais, vastamente discutidos na literatura, como Amortecimento Exponencial e modelos ARIMA e projetar cenários para avaliar como as variáveis explicativas presentes no modelo de Regressão Dinâmica proposto neste estudo afetam o frete marítimo. O produto desenvolvido nesta dissertação mostrou a viabilidade de os modelos univariados e causais serem utilizados como ferramenta de previsão da taxa frete de navios petroleiros. Como forma de validação, os resultados foram comparados aos obtidos com a metodologia vigente em uma grande empresa de petróleo do Brasil. O protótipo de sistema de previsão proposto, via Regressão Dinâmica, apresentou resultados satisfatórios e desempenho superior ao obtido através da metodologia da empresa de petróleo.<br>Crude oil and oil products seaborne transportation is a key component of the petroleum industry supply chain, integrating suppliers and customers located in different geographic regions. In this context, the freight rates practiced have a great impact on the international trade of these goods. This work aims to verify the performance of Dynamic Regression models in short-term maritime freight forecasts of the spot market of an oil export route from West Africa to China, to compare the predictive capacity of the model with traditional methods, widely discussed in the literature, such as Exponential Smoothing and ARIMA models and to design scenarios to evaluate how the explanatory variables present in the Dynamic Regression model proposed in this study affect freight rate. The product developed in this dissertation showed the viability of the univariate and causal models being used as a forecasting tool for the oil tankers freight rate. As a form of validation, the results were compared to those obtained with the methodology of a large Brazilian oil company. The proposed prediction system prototype, through Dynamic Regression model, presented satisfactory results and performance superior to that obtained through the methodology of the oil company.
38
Chartier, Alex. "Ionospheric specification and forecasting." Thesis, University of Bath, 2013. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.629652.
Full textAbstract:
Space weather presents a threat to human activities such as Global Navigation Satellite System (GNSS) positioning and timing, power systems, radio communications and transpolar aviation. Nowcasts and forecasts of the ionosphere could help mitigate some of these damaging effects. In this thesis, state-of-the-art ionospheric specification techniques are assessed in a long-term study. That study shows that Global Positioning System (GPS) derived tomographic images specify monthly median ionospheric Total Electron Content (TEC) accurately in Europe and North America throughout the twelve-year test period. Following this assessment, developments are presented in three key areas. The resolution of horizontal structures in ionospheric images over Africa is assessed. The accuracy gains from adding receivers are quantified using a simulation approach, showing that an extended GPS network reduces Root-Mean-Square (RMS) error from 9.5 TEC units for the currently operational network to 4.5 TEC units. A fictional, ideal network is demonstrated to produce images with RMS errors of 3.0 TEC units. Images of the vertical electron density distribution, vital for High Frequency (HF) radio operators, are greatly improved by adding observations of the ionospheric vertical profile to an imaging algorithm that relies on GPS observations. The peak electron density is resolved to an RMS accuracy of 0.5 x 1011 electrons/m3, compared to an RMS accuracy of 1.0 x 1011 electrons/m3 for the standard approach. A novel experimental method is employed to show that forecasts of ionospheric storms could benefit significantly from accurate specification of the initial neutral composition, in particular the ratio of O to N2 . A theoretical experiment shows that an ideal assimilation of the thermospheric composition can improve storm-time forecasts by at least 10% for over 19 hours, whilst an ideal ionospheric assimilation improves forecasts for less than four hours. This finding will aid the development of a coupled thermosphere ionosphere forecast system.
39
Velonias, Platon M. (Platon Michael). "Forecasting tanker freight rates." Thesis, Massachusetts Institute of Technology, 1995. http://hdl.handle.net/1721.1/36016.
Full text
40
Souza, André B. M. "Essays in economic forecasting." Doctoral thesis, Universitat Pompeu Fabra, 2021. http://hdl.handle.net/10803/672997.
Full textAbstract:
This dissertation consists of two independent chapters on economic and financial
forecasting. The first chapter introduces a nonlinear forecasting framework
that combines forecasts of the sign and absolute value of a time series into conditional
mean forecasts. In contrast to linear models, the proposed framework
allows different predictors to separately impact the sign and absolute value of the
target series. An empirical application using the FRED-MD dataset shows that
forecasts from the proposed model substantially outperform linear forecasts for
series that exhibit persistent volatility dynamics, such as output and interest rates.
The second chapter, coauthored with Christian Brownlees, provides an extensive
comparison of methods to forecast downside risks to GDP growth for a panel of
24 OECD economies. We consider forecasts constructed from standard quantile
regressions as well as from conditional volatility models. Our evidence suggests
that standard volatility models such as the GARCH(1,1) are at least as accurate as
quantile regressions.<br>Aquesta dissertació consta de dos capítols independents sobre previsió econòmica
i financera. El primer capítol introdueix un modelo de predicció
no lineal que
combina les previsions del signe i del valor absolut d’una sèrie temporal en previsions mitjanes
condicionals. A diferència dels models lineals, el modelo proposat permet que diferents variables
afectin per separat el signe i el valor absolut de la sèrie d’interés. Una aplicació empírica
que utilitza el conjunt de dades FRED-MD mostra que les previsions basades en el modelo proposat
superen substancialment les previsions lineals per a sèries que presenten dinàmiques de
volatilitat persistents, com la producció industrial i els tipus d’interès. El segon capítol,
coautorado con Christian Brownlees, proporciona una àmplia comparació
de mètodes
per predir els riscos negatius per al creixement del PIB per a un grup de 24 economies de l’OCDE.
Considerem les previsions construïdes a partir de regressions quàntils estàndard, així com a
partir de models de volatilitat condicional. La nostra evidència suggereix que els models de
volatilitat, com el GARCH (1,1), són almenys tan precisos com les regressions quantils.
41
Walker, Jacob Charles. "Data-Driven Visual Forecasting." Research Showcase @ CMU, 2018. http://repository.cmu.edu/dissertations/1221.
Full textAbstract:
Understanding the temporal dimension of images is a fundamental part of computer vision. Humans are able to interpret howthe entities in an image will change over time. However, it has only been relatively recently that researchers have focused on visual forecasting— getting machines to anticipate events in the visual world before they actually happen. This aspect of vision has many practical implications for tasks ranging from human-computer interaction to anomaly detection. In addition, temporal prediction can serve as a task for representation learning, useful for various other recognition problems. In this thesis, we focus on visual forecasting that is data-driven, self-supervised, and relies on little to no explicit semantic information. Towards this goal, we explore prediction at different timeframes. We first consider predicting instantaneous pixelmotion—optical flow. We apply convolutional neural networks to predict optical flow in static images. We then extend this idea to a longer timeframe, generalizing to pixel trajectory prediction in spacetime. We incorporate models such as variational autoencoders to generate future possible motions in the scene. After this, we consider a mid-level element approach to forecasting. By combining a Markovian reasoning framework with an intermediate representation, we are able to forecast events over longer timescales. This dissertation then builds upon these ideas towards structured representations for visual forecasting. Specifically, we aim to reason about the future of images in a structured state space. Instead of directly predicting events in a low-level feature space such as pixels or motion, we forecast events in a higher level representation that is still visually meaningful. This approach confers a number of advantages. It is not restricted by explicit timescales like motion-based approaches, and, unlike direct pixel-based approaches, predictions are less likely to “fall off” the manifold of the true visual world.
42
Furman, Yoel Avraham. "Forecasting with large datasets." Thesis, University of Oxford, 2014. http://ora.ox.ac.uk/objects/uuid:69f2833b-cc53-457a-8426-37c06df85bc2.
Full textAbstract:
This thesis analyzes estimation methods and testing procedures for handling large data series. The first chapter introduces the use of the adaptive elastic net, and the penalized regression methods nested within it, for estimating sparse vector autoregressions. That chapter shows that under suitable conditions on the data generating process this estimation method satisfies an oracle property. Furthermore, it is shown that the bootstrap can be used to accurately conduct inference on the estimated parameters. These properties are used to show that structural VAR analysis can also be validly conducted, allowing for accurate measures of policy response. The strength of these estimation methods is demonstrated in a numerical study and on U.S. macroeconomic data. The second chapter continues in a similar vein, using the elastic net to estimate sparse vector autoregressions of realized variances to construct volatility forecasts. It is shown that the use of volatility spillovers estimated by the elastic net delivers substantial improvements in forecast ability, and can be used to indicate systemic risk among a group of assets. The model is estimated on realized variances of equities of U.S. financial institutions, where it is shown that the estimated parameters translate into two novel indicators of systemic risk. The third chapter discusses the use of the bootstrap as an alternative to asymptotic Wald-type tests. It is shown that the bootstrap is particularly useful in situations with many restrictions, such as tests of equal conditional predictive ability that make use of many orthogonal variables, or `test functions'. The testing procedure is analyzed in a Monte Carlo study and is used to test the relevance of real variables in forecasting U.S. inflation.
43
Chala, A. V. "Classified forecasting exchange rate." Thesis, Видавництво СумДУ, 2012. http://essuir.sumdu.edu.ua/handle/123456789/26081.
Full text
44
Sharma, Namit. "Forecasting Oil Price Volatility." Thesis, Virginia Tech, 1998. http://hdl.handle.net/10919/36815.
Full textAbstract:
This study compares different methods of forecasting price volatility in the crude oil futures market using daily data for the period November 1986 through March 1997. It compares the forward-looking implied volatility measure with two backward-looking time-series measures based on past returns - a simple historical volatility estimator and a set of estimators based on the Generalized Autoregressive Conditional Heteroscedasticity (GARCH) class of models.
<p>
Tests for the relative information content of implied volatilities vis-Ã -vis GARCH time series models are conducted within-sample by estimating nested conditional variance equations with returns information and implied volatilities as explanatory variables. Likelihood ratio tests indicate that both implied volatilities and past returns contribute volatility information. The study also checks for and confirms that the conditional Generalized Error Distribution (GED) better describes fat-tailed returns in the crude oil market as compared to the conditional normal distribution.
<p>
Out-of-sample forecasts of volatility using the GARCH GED model, implied volatility, and historical volatility are compared with realized volatility over two-week and four-week horizons to determine forecast accuracy. Forecasts are also evaluated for predictive power by regressing realized volatility on the forecasts. GARCH forecasts, though superior to historical volatility, do not perform as well as implied volatility over the two-week horizon. In the four-week case, historical volatility outperforms both of the other measures. Tests of relative information content show that for both forecast horizons, a combination of implied volatility and historical volatility leaves little information to be added by the GARCH model.<br>Master of Arts
45
Hellman, Simon. "Forecasting conflict using RNNs." Thesis, Uppsala universitet, Signaler och system, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-445859.
Full textAbstract:
The rise in machine learning has made the subject interesting for new types of uses. This Master thesis implements and evaluates an LSTM-based algorithm on the conflict forecasting problem. Data is structured in country-month pairs, with information about conflict, economy, demography, democracy and unrest. The goal is to forecast the probability of at least one conflict event in a country based on a window of historic information. Results show that the model is not as good as a Random Forest. There are also indications of a lack of data with the network having difficulty performing consistently and with learning curves not flattening. Naive models perform surprisingly well. The conclusion is that the problem needs some restructuring in order to improve performance compared to naive approaches. To help this endeavourpossible paths for future work has been identified.
46
Ahmadi-Djam, Adrian, and Nordström Sean Belfrage. "Forecasting Non-Maturing Liabilities." Thesis, KTH, Matematisk statistik, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-205032.
Full textAbstract:
With ever increasing regulatory pressure financial institutions are required to carefully monitor their liquidity risk. This Master thesis focuses on asserting the appropriateness of time series models for forecasting deposit volumes by using data from one undisclosed financial institution. Holt-Winters, Stochastic Factor, ARIMA and ARIMAX models are considered with the latter being the one with best out-of-sample performance. The ARIMAX model is appropriate for forecasting deposit volumes on a 3 to 6 month horizon with seasonality accounted for through monthly dummy variables. Explanatory variables such as market volatility and interest rates do improve model accuracy but vastly increases complexity due to the simulations needed for forecasting.<br>Med ständigt ökande krav på finansiella institutioner måste de noga övervaka sin likviditetsrisk. Detta examensarbete fokuserar på att analysera lämpligheten av tidsseriemodeller för prognoser inlåningsvolymer med hjälp av data från en ej namngiven finansiell institution. Holt-Winters, Stochastic Factor, ARIMA och ARIMAX modellerna används, där den senare uppvisar bäst resultat. ARIMAX modellen är lämplig för prognoser av inlåningsvolymer på en 3-6 månaders tidshorisont där hänsyn till säsongseffekter tagits genom månatliga dummyvariabler. Förklaringsvariabler såsom marknadsvolatilitet och räntor förbättrar modellens prognosticeringsprecision men ökar samtidigt komplexiteten på grund av de simuleringar som krävs.
47
Dror, Marika. "Forecasting of exchange rates." Doctoral thesis, Vysoká škola ekonomická v Praze, 2010. http://www.nusl.cz/ntk/nusl-202335.
Full textAbstract:
The thesis investigates different exchange rate models and their forecasting performance. The work takes previous literature overview and summarize their findings. Despite the significant amount of papers which were done on the topic of exchange rate forecast, basically none of them cannot find an appropriate model which would outperform a forecast of a simple random walk in every horizon or for any currency pair. However, there are some positive findings in specific cases (e.g. for specific pair or for specific time horizon). The study provides up-to-date analysis of four exchange rates (USD/CZK, USD/ILS, USD/GBP and USD/EUR) for the period of time from January 2000 to August 2013 and analyse forecasting performance of seven exchange rate models (uncovered interest rate parity model, purchasing power parity model, monetary model, monetary model with error correction, Taylor rule model, hidden Markov model and ESTAR model). Although, the results are in advantage of Taylor rule model, especially for the exchange rate of USD/CZK, I cannot prove that the forecasting performance is significantly better than the random walk model. Except of the overall analysis, the work suppose instabilities in the time. Stock and Watson (2003) found that the forecast predictability is not stable over time. As a consequence, the econometric model can give us better forecast than random walk process at some period of time, however at other period, the forecasting ability can be worse than random walk. Based on Fluctuation test of Giacomini and Rossi (2010a) every model is analysed how the out-of-sample forecast ability changes over time.
48
Simoes, Nuno Eduardo da Cruz. "Urban pluvial flood forecasting." Thesis, Imperial College London, 2012. http://hdl.handle.net/10044/1/10545.
Full textAbstract:
Two main approaches to enhance urban pluvial flood prediction were developed and tested in this research: (1) short-term rainfall forecast based on rain gauge networks, and (2) customisation of urban drainage models to improve hydraulic simulation speed. Rain gauges and level gauges were installed in the Coimbra (Portugal) and Redbridge (UK) catchment areas. The collected data was used to test and validate the approaches developed. When radar data is not available urban pluvial flooding forecasting can be based on networks of rain gauges. Improvements were made in the Support Vector Machine (SVM) technique to extrapolate rainfall time series. These improvements are: enhancing SVM prediction using Singular Spectrum Analysis (SSA) for pre-processing data; combining SSA and SVM with a statistical analysis that gives stochastic results. A method that integrates the SVM and Cascade-based downscaling techniques was also developed to carry out high-resolution (5-min) precipitation forecasting with longer lead time. Tests carried out with historical data showed that the new stochastic approach was useful for estimating the level of confidence of the rainfall forecast. The integration of the cascade method demonstrates the possibility of generating high-resolution rainfall forecasts with longer lead time. Tests carried out with the collected data showed that water level in sewers can be predicted: 30 minutes in advance (in Coimbra), and 45 minutes in advance (in Redbridge). A method for simplifying 1D1D networks is presented that increases computational speed while maintaining good accuracy. A new hybrid model concept was developed which combines 1D1D and 1D2D approaches in the same model to achieve a balance between runtime and accuracy. While the 1D2D model runs in about 45 minutes in Redbridge, the 1D1D and the hybrid models both run in less than 5 minutes, making this new model suitable for flood forecasting.
49
Syntetos, Argyrios. "Forecasting of intermittent demand." Thesis, Online version, 2001. http://bibpurl.oclc.org/web/26215.
Full text
50
Liao, Kua-ping. "Feedforward neural network forecasting model building evaluation : theory and application in business forecasting." Thesis, Lancaster University, 1999. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.310532.
Full text