To see the other types of publications on this topic, follow the link: Trading automatisé.
Dissertations / Theses on the topic 'Trading automatisé'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 37 dissertations / theses for your research on the topic 'Trading automatisé.'
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
Tran, Trung-Minh. "Contributions to Agent-Based Modeling and Its Application in Financial Market." Electronic Thesis or Diss., Université Paris sciences et lettres, 2023. http://www.theses.fr/2023UPSLP022.
Full textAbstract:
L'analyse de modèles complexes tels que les marchés financiers aide les gestionnaires à élaborer des politiques raisonnables et les commerçants à choisir des stratégies de négociation efficaces. La modélisation basée sur les agents est une méthodologie de calcul pour modéliser des systèmes complexes et analyser l'influence de différentes hypothèses sur les comportements des agents. Dans le cadre de cette thèse, nous considérons un modèle de marché financier qui comprend 3 types d'agents : les agents techniques, les agents fondamentaux et les agents de bruit. Nous commençons par l'agent technique avec le défi d'optimiser une stratégie de trading basée sur l'analyse technique à travers un système de trading automatisé. Ensuite, les méthodes d'optimisation proposées sont appliquées avec des fonctions objectives appropriées pour optimiser les paramètres du modèle ABM. L'étude a été menée avec un modèle ABM simple incluant uniquement des agents de bruit, puis le modèle a été étendu pour inclure différents types d'agents. La première partie de la thèse étudie le comportement commercial des agents techniques. Différentes approches sont introduites telles que : l'algorithme génétique, l'optimisation bayésienne et l'apprentissage par renforcement profond. Les stratégies de trading sont construites sur la base d'un indicateur avancé, Relative Strength Index, et de deux indicateurs retardés, Bollinger Band et Moving Average Convergence-Divergence. De multiples expériences sont réalisées sur différents marchés, notamment : le marché des crypto-monnaies, le marché boursier et le marché des contrats à terme cryptographiques. Les résultats montrent que les stratégies optimisées à partir des approches proposées peuvent générer des rendements plus élevés que leur forme typique et la stratégie Buy and Hold. En utilisant les résultats de l'optimisation des stratégies de trading, nous proposons une nouvelle approche pour optimiser les paramètres du modèle à base d'agents. La deuxième partie de la thèse présente une application de la modélisation multiagents au marché boursier. En conséquence, nous avons montré que les modèles ABM peuvent être optimisés en utilisant la méthode d'optimisation bayésienne avec plusieurs fonctions objectives. Les faits stylisés du marché réel peuvent être reproduits en construisant soigneusement les fonctions objectives de l'agent. Notre travail comprend le développement d'un environnement, les comportements des différents agents et leurs interactions. La méthode d'optimisation bayésienne avec le test de Kolmogorov-Smirnov comme fonction objective a montré des avantages et un potentiel dans l'estimation d'un ensemble optimal de paramètres pour un modèle de marché financier artificiel. Le modèle que nous proposons est capable de reproduire les faits stylisés du marché réel. En outre, un nouveau fait stylisé sur la proportion de commerçants sur le marché est présenté. Avec les données empiriques de l'indice Dow Jones Industrial Average, nous avons constaté que les traders fondamentaux représentent 9%-11% de tous les traders du marché boursier. À l'avenir, davantage de recherches seront menées pour améliorer le modèle et les méthodes d'optimisation, telles que l'application de modèles d'apprentissage automatique, l'apprentissage par renforcement multiagents ou l'examen de l'application sur différents marchés et instruments négociésThe analysis of complex models such as financial markets helps managers to make reasonable policies and traders to choose effective trading strategies. Agent-based modeling is a computational methodology to model complex systems and analyze the influence of different assumptions on the behaviors of agents. In the scope of this thesis, we consider a financial market model that includes 3 types of agent: technical agents, fundamental agents and noise agents. We start with the technical agent with the challenge of optimizing a trading strategy based on technical analysis through an automated trading system. Then, the proposed optimization methods are applied with suitable objective functions to optimize the parameters for the ABM model. The study was conducted with a simple ABM model including only noise agents, then the model was extended to include different types of agents. The first part of the thesis investigates the trading behavior of technical agents. Different approaches are introduced such as: Genetic Algorithm, Bayesian Optimization and Deep Reinforcement Learning. The trading strategies are built based on a leading indicator, Relative Strength Index, and two lagging indicators, Bollinger Band and Moving Average Convergence-Divergence. Multiple experiments are performed in different markets including: cryptocurrency market, stock market and crypto futures market. The results show that optimized strategies from proposed approaches can generate higher returns than their typical form and Buy and Hold strategy. Using the results from the optimization of trading strategies, we propose a new approach to optimize the parameters of the agent-based model. The second part of the thesis presents an application of agent-based modeling to the stock market. As a result, we have shown that ABM models can be optimized using the Bayesian Optimization method with multiple objective functions. The stylized facts of the actual market can be reproduced by carefully constructing the objective functions of the agent. Our work includes the development of an environment, the behaviors of different agents and their interactions. Bayesian optimization method with Kolmogorov-Smirnov test as objective function has shown advantages and potential in estimating an optimal set of parameters for an artificial financial market model. The model we propose is capable of reproducing the stylized facts of the real market. Furthermore, a new stylized fact about the proportion of traders in the market is presented. With empirical data of the Dow Jones Industrial Average index, we found that fundamental traders account for 9%-11% of all traders in the stock market. In the future, more research will be done to improve the model and optimization methods, such as applying machine learning models, multi-agent reinforcement learning or considering the application in different markets and traded instruments
2
Larsen, Fredrik. "Automatic stock market trading based on Technical Analysis." Thesis, Norwegian University of Science and Technology, Department of Computer and Information Science, 2007. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-8707.
Full textAbstract:
The theory of technical analysis suggests that future stock price developement can be foretold by analyzing historical price fluctuations and identifying repetitive patterns. A computerized system, able to produce trade recommendations based on different aspects of this theory, has been implemented. The system utilizes trading agents, trained using machine learning techniques, capable of producing unified buy and sell signals. It has been evaluated using actual trade data from the Oslo Børs stock exchange over the period 1999-2006. Compared to the simple strategy of buying and holding, some of the agents have proven to yield good results, both during years with extremely good stock market returns, as well as during times of recession. In spite of the positive performance, anomalous results do exist and call for cautionous use of the system’s recommendations. Combining them with fundamental analysis appears to be a safe approach to achieve succesful stock market trading.
3
Sauer, Václav. "Tvorba obchodní strategie pro měnový trh." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2017. http://www.nusl.cz/ntk/nusl-318623.
Full textAbstract:
This thesis deals with the design, implementation and optimization of the automated trading system for the foreign exchange market. Thesis analyses theoretical aspects for the system implementation, including introduction of foreign exchange market, types of market analysis, money management, risk management and technical indicators. The thesis further describes, what is required for development of such system and what important parts the system must contain. The work also describes how the system can be tested and optimised based on historical data.
4
Raykhel, Ilya. "Real-time automatic price prediction for eBay online trading /." Diss., CLICK HERE for online access, 2008. http://contentdm.lib.byu.edu/ETD/image/etd2697.pdf.
Full text
5
Raykhel, Ilya Igorevitch. "Real-Time Automatic Price Prediction for eBay Online Trading." BYU ScholarsArchive, 2008. https://scholarsarchive.byu.edu/etd/1631.
Full textAbstract:
While Machine Learning is one of the most popular research areas in Computer Science, there are still only a few deployed applications intended for use by the general public. We have developed an exemplary application that can be directly applied to eBay trading. Our system predicts how much an item would sell for on eBay based on that item's attributes. We ran our experiments on the eBay laptop category, with prior trades used as training data. The system implements a feature-weighted k-Nearest Neighbor algorithm, using genetic algorithms to determine feature weights. Our results demonstrate an average prediction error of 16%; we have also shown that this application greatly reduces the time a reseller would need to spend on trading activities, since the bulk of market research is now done automatically with the help of the learned model.
6
Trnik, Erik. "Návrh a optimalizace automatického obchodního systému pro forex." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2017. http://www.nusl.cz/ntk/nusl-318583.
Full textAbstract:
The master's thesis deals with the design of the proposed automatic trading system especially for daily trading on the currency markets. The aim of the thesis is to create a complex theoretical basis, in the practical part of the work to use the knowledge to create a suitable automatic trading system. The thesis focuses on the technical analysis of the currency markets. The proposed system will be optimally optimized to maximize profitability and stability with application to the most liquid currency pairs.
7
Parro, Mattia <1991>. "Analisi tecnica e trading systems - sviluppo di un sistema di trading automatico basato sulla conformazione grafica a bandiera." Master's Degree Thesis, Università Ca' Foscari Venezia, 2021. http://hdl.handle.net/10579/18525.
Full textAbstract:
Trasformazione di una formazione grafica dei prezzi, la conformazione a bandiera, in un trading system automatizzato.
Analisi dei risultati e confronto dei rendimenti con la strategia di investimento basata sul buy&hold
8
PINTO, THIAGO REZENDE. "APPLICATION OF NONLINEAR MODELS FOR AUTOMATIC TRADING IN THE BRAZILIAN STOCK MARKET." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2006. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=9141@1.
Full textAbstract:
CONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICOEsta dissertação tem por objetivo comparar o desempenho de modelos não lineares de previsão de retornos em 10 ativos do mercado acionário brasileiro. Entre os modelos escolhidos, pode-se citar o STAR-Tree, que combina conceitos da metodologia STAR (Smooth Transition AutoRegression) e do algoritmo CART (Classification And Regression Trees), tendo como resultado final uma regressão com transição suave entre múltiplos regimes. A especificação do modelo é feita através de testes de hipótese do tipo Multiplicador de Lagrange que indicam o nó a ser dividido e a variável explicativa correspondente. A estimação dos parâmetros é feita pelo método de Mínimos Quadrados Não Lineares para determinar o valor dos parâmetros lineares e não lineares. Redes Neurais, modelos ARMAX (estes lineares) e ainda o método Naive também foram incluídos na análise. Os resultados das previsões foram avaliados a partir de medidas estatísticas e financeiras e se basearam em um negociador automático que informa o instante correto de assumir uma posição comprada ou vendida em cada ativo. Os melhores desempenhos foram alcançados pelas Redes Neurais, pelos modelos ARMAX e pela forma de previsão ARC (Adaptative Regime Combination) derivada da metodologia STAR-Tree, sendo ambos ainda superiores ao retorno das ações durante o período de teste
The goal of this dissertation is to compare the performance of non linear models to forecast return on 10 equities in the Brazilian Stock Market. Among the chosen ones, it can be cited the STAR-Tree, which matches concepts from the STAR (Smooth Transition AutoRegression) methodology and the CART (Classification And Regression Trees) algorithm, having as the resultant structure a regression with smooth transition among multiple regimes. The model specification is done by Lagrange Multiplier hypothesis tests that indicate the node to be splitted and the corresponding explanatory variable. The parameter estimation is done by the Non Linear Least Squares method that determine the linear and non linear parameters. Neural Netwoks, ARMAX models (these ones linear) and the Naive method were also included in the analysis. The forecasting results were calculated using statistical and financial measures and were based on an automatic negociator that signaled the right instant to take a short or a long position in each stock. The best results were reached by the Neural Networks, ARMAX models and ARC (Adaptative Regime Combination ) forecasting method derived from STAR-Tree, with all of them performing better then the equity return during the test period.
9
EPPRECHT, CAMILA ROSA. "MEAN AND REALIZED VOLATILITY SMOOTH TRANSITION MODELS APPLIED TO RETURN FORECASTING AND AUTOMATIC TRADING." PONTIFÍCIA UNIVERSIDADE CATÓLICA DO RIO DE JANEIRO, 2008. http://www.maxwell.vrac.puc-rio.br/Busca_etds.php?strSecao=resultado&nrSeq=13209@1.
Full textAbstract:
COORDENAÇÃO DE APERFEIÇOAMENTO DO PESSOAL DE ENSINO SUPERIORCONSELHO NACIONAL DE DESENVOLVIMENTO CIENTÍFICO E TECNOLÓGICO
O principal objetivo desta dissertação é comparar o desempenho de modelos lineares e não-lineares de previsão de retornos de 23 ativos do mercado acionário americano. Propõe-se o modelo STAR-Tree Heterocedástico, que faz uso da metodologia do STAR-Tree (Smooth Transition AutoRegression Tree) aplicada a séries temporais heterocedásticas. Com a disponibilidade de dados de retorno e da volatilidade realizada de ações intra-diários, as séries de retornos são transformadas através da divisão de cada retorno pela sua volatilidade realizada. A série transformada apresenta variância constante. O modelo é uma combinação da metodologia STAR (Smooth Transition AutoRegression) e do algoritmo CART (Classification and Regression Tree). O modelo resultante pode ser interpretado como uma regressão de múltiplos regimes com transição suave. A especificação do modelo é feita através de testes de Multiplicadores de Lagrange, que indicam o nó a ser dividido e a variável de transição correspondente. Os modelos de comparação usados são o modelo Média, o método Naive, modelos lineares ARX e Redes Neurais. As previsões dos modelos foram avaliadas através de medidas estatísticas e financeiras. Os resultados financeiros baseam-se em uma regra de negociação automática que informa o momento de comprar e vender cada ativo. O modelo STAR-Tree Heterocedástico teve resultados estatísticos equivalentes aos dos outros modelos, porém apresentou um desempenho financeiro superior para a maioria das séries. A volatilidade realizada também foi estimada usando a metodologia STAR-Tree, e sua previsão foi utilizada para fazer uma análise de alavancagem financeira.
The main goal of this dissertation is to compare the performance of linear and nonlinear models to forecast 23 assets of the American Stocks Market. The Heteroscedastic STAR-Tree Model is proposed using the STAR- Tree (Smooth Transition AutoRegression Tree) methodology applied to heteroscedastic time series. As assets returns and realized volatility intraday data are available, the returns series are transformed by dividing each return by its realized volatility, which gives homocedastic series. The model is a combination of the STAR (Smooth Transition AutoRegression) methodology and the CART (Classification and Regression Tree) algorithm. The resulting model can be interpreted as a smooth transition multiple regime regression. The model specification is done by Lagrange Multiplier tests that indicate the node to be split and the corresponding transition variable. The comparison models used are the Mean model, Naive method, ARX linear models and Neural Networks. The forecasting models were evaluated through statistical and financial measures. The financial results are based on an automatic trading rule that signals buy and hold moments in each stock. The Heteroscedastic STAR-Tree Model statistical performance was equivalent to the other models, however its financial performance was superior for most of the series. The STAR-Tree methodology was also applied for forecasting the realized volatility, and the forecasts were used in financial leverage analysis.
10
Myslivec, Oldřich. "Využití technické analýzy při tvorbě obchodních systémů." Master's thesis, Vysoká škola ekonomická v Praze, 2009. http://www.nusl.cz/ntk/nusl-11194.
Full textAbstract:
This thesis is devoted to the technical analysis with the emphasis on design, testing and using of trading systems. Its objective is to find out whether it is possible for a trader to design and trade his own profitable trading system with widely accessible tools and methods. First part of the thesis is focused on the chart analysis and description of candlestick charts including their rate of profit success, all based on hands-on experience in a real market. It continues with a breakdown of most used methods based on moving averages. The second chapter fully describes main stage of trading system development and follows up with third chapter on practical application of the theoretical assumption on the real market conditions, i.e. to design a profitable trading system
11
Thouillez, Thomas. "Anatomie des marchés financiers à haute fréquence : analyse de l'Influence de l'automatisation sur la microstructure des marchés financiers." Thesis, Paris 1, 2020. http://www.theses.fr/2020PA01E049.
Full textAbstract:
Cette thèse étudie les principales transformations de la microstructure des marchés financiers depuis la généralisation de l’automatisation des marchés. Aujourd'hui, la modification structurelle des marchés financiers, associée à l'évolution des technologies de l'information, ont entrainé des bouleversements, tant dans les pratiques de marchés, que dans les instruments de mesures de la qualité de marché. Le coût de la liquidité a continué de s’améliorer entre 2010 et 2019, notamment en réduisant les spreads des sociétés moins importantes du SBF 120. En revanche, les spreads effectifs se réduisent nettement moins montrant la faible profondeur du carnet d’ordres aux meilleures limites pour les entreprises les plus petites. Les travaux présentent les mutations des plateformes de négociation et les évolutions technologiques qui ont permis le déploiement du trading haute-fréquence. L’équipe de recherche a développé un outil de réplication des marchés financiers, VirteK. La librairie a permis une simulation répliquant les faits stylisés du flash-crash du 6 mai 2010 illustrant les déséquilibres du carnet d’ordres à l’aide du VPINThis thesis studies major market microstructure transformations since the automation of financial markets. Today, structural modification of financial markets, associated with the improvement of information and communication technology, lead to important shifts regarding market practices, and market quality measures. Liquidity costs continued to improve between 2010 and 2019, reducing quoted spread especially for SBF 120 small capitalizations. However, effective spreads decreased significantly less than quoted spreads for those small cap proving the weak resilience of the order book on the best limits. This work presents execution venues transformation and technological evolutions to implement high-frequency trading. The research team built a financial market replicating library called VirteK. This library helped to recover stylized facts from the May 6, 2010 flash-crash illustrating limit order book imbalances with the VPIN measure
12
Křesťan, Zdeněk. "Automatizované obchodování na kryptoměnových burzách." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2018. http://www.nusl.cz/ntk/nusl-385948.
Full textAbstract:
This thesis focuses on automated trading on cryptocurrency exchanges. Cryptos are now widespread. The possibility of hier automated buying and selling is an interesting topic, which is more and more mentioned. The main part of the thesis is the design of an algorithm for processing data from stock exchanges, their evaluation and subsequent execution of cryptocurrency trades. It also describes its implementation, testing and possible further extensions.
13
Facchini, Nicolo' <1995>. "Machine learning ed investimenti finanziari - Studio ed elaborazione di trading system automatici basati su reinforcement learning ed analisi tecnica." Master's Degree Thesis, Università Ca' Foscari Venezia, 2020. http://hdl.handle.net/10579/16547.
Full textAbstract:
La presente tesi di laurea ha il fine di analizzare e rielaborare la letteratura scientifica in merito all’applicazione di modelli di reinforcement learning in trading system automatici. Dopo aver descritto le caratteristiche dei modelli di machine learning e dei trading system finanziari a tutto tondo (con particolare riguardo, rispettivamente, al reinforcement learning ed all’analisi tecnica), il lavoro di ricerca verterà sulla personale elaborazione di sistemi d’investimento basati su tali concetti. Nel primo capitolo il focus è sul tema del machine learning, analizzato nelle sue diverse varianti ed applicazioni, ovviamente con grande attenzione al reinforcement learning. Il secondo, invece, si concentra sulla descrizione dei trading system proposti nel corso degli anni, in particolare, con l’utilizzo di indicatori di analisi tecnica. Nel terzo capitolo vengono descritte la creazione ed applicazione di trading system automatici che combinano reinforcement learning, analisi tecnica e diverse soluzioni per l’implementazione dei modelli già proposti in letteratura. Con il quarto capitolo, infine, si espongono i risultati ottenuti, confrontando l’utilizzo dei modelli ideati con metodi tradizionali di investimento e trading system di origine precedente. Attraverso queste quattro fasi di approfondimento verranno proposti, in conclusione, una valutazione sull’applicazione dei suddetti modelli ed eventuali implementazioni future.
14
Dekýš, Marek. "Návrh automatického obchodního systému na měnových trzích s využitím breakout strategie." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2015. http://www.nusl.cz/ntk/nusl-224982.
Full textAbstract:
This thesis addresses the analysis and design of automatic trading system on currency markets using breakout strategy for capital appreciation for company ALFA – zdravá výživa. The description of implementation of this strategy on chosen trading platform and its summary will represent an output of this thesis.
15
Kříž, Jakub. "Algoritmické obchodování na burze s využitím dat z Twitteru." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2015. http://www.nusl.cz/ntk/nusl-264940.
Full textAbstract:
This master's thesis describes creation of prediction system. This system predicts future market development based on stock exchange data and twitter messages analysis. Tweets from two different sources are analysed by mood dictionaries or via recurrent neural networks. This analysis results and technical analysis of stock exchange data results are used in multilayer neural network for prediction. A business strategy is created and tested based on results of this prediction. Design and implementation of prediction system is described in this thesis. This system achieved revenue increase more than 25 % of some business strategies by tweets analysis. However this improvement applies for certain data and timeframe.
16
Nečas, Ondřej. "Návrh automatického obchodního systému měnové burzy." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2015. http://www.nusl.cz/ntk/nusl-225269.
Full textAbstract:
The content of this diploma thesis is building an automatic trading system and its exact description. The thesis is focused on the classification of system requirements and on this base selection of underlying asset, which is defined by the forex contracts category.
17
Malý, Petr. "Návrh automatického obchodního systému s využitím fraktální geometrie." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2015. http://www.nusl.cz/ntk/nusl-224844.
Full textAbstract:
This thesis deals with an analysis and prediction of foreign exchange markets. The thesis is based on the fractal market hypothesis and it uses tools based on fractal geometry for prediction of markets. The thesis also describes ways of using advanced methods of artificial intelligence for analyzing markets. The outcome is designed and implemented automatic trading system. The thesis also deals with testing of designed system on historical data and on the latest data as well.
18
Vlček, Tomáš. "Podpora v rozhodování pro investičního experta na měnových trzích." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2014. http://www.nusl.cz/ntk/nusl-224707.
Full textAbstract:
The thesis focuses on automated trading systems for trading on currency market. It describes basics of market analysis and deals with the design, optimization and identifying appropriate indicators of automatic trading system, which is based on the Fibonacci retracement. This system should serve as a decision support for trader's operations in the currency market. Furthermore, this thesis deals with the possibility of avoiding exchange rate risk by trading in the foreign exchange market.
19
Štechr, Vladislav. "Využití SVM v prostředí finančních trhů." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2016. http://www.nusl.cz/ntk/nusl-241651.
Full textAbstract:
This thesis deals with use of regression or classification based on support vector machines from machine learning field. SVMs predict values that are used for decisions of automatic trading system. Regression and classification are evaluated for their usability for decision making. Strategy is being then optimized, tested and evaluated on foreign exchange market Forex historic data set. Results are promising. Strategy could be used in combination with other strategy that would confirm decisions for entering and exiting trades.
20
Kněžínek, Michal. "Návrh a využití automatického obchodního systému pro zhodnocení kapitálu podniku." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2014. http://www.nusl.cz/ntk/nusl-224710.
Full textAbstract:
This diploma thesis discusses about the possibilities of investing in the capital market with a focus on the foreign exchange market. Analysis of the company, whose output is SWOT analysis, is focused on the economic justification of investments. The essence is the proposal of automatic trading systems that will automatically trade on the basis of information from the market and add value to ivested capital. This automatic trading systems are designed in analytic platform named MetaTrader and their parameters are optimized by genetic algorithms.
21
Boček, František. "Návrh a optimalizace automatického obchodního systému." Master's thesis, Vysoké učení technické v Brně. Fakulta podnikatelská, 2016. http://www.nusl.cz/ntk/nusl-241636.
Full textAbstract:
The goal of this work is to describe approaches to financial market analysis and implement chosen approaches in automatic trading system in the MetaQuote Language environment for Metatrader platform. Another objective is to optimise the designed trading system and test additional rules to achieve maximum profit during minimalization risks.
22
Pinheiro, Joel Coelho. "iTrading." Master's thesis, Universidade de Aveiro, 2016. http://hdl.handle.net/10773/17263.
Full textAbstract:
Mestrado em Engenharia de Computadores e TelemáticaA Internet permitiu revolucionar várias áreas económicas graças à facilidade com que é possível distribuir informação e comunicar entre entidades. Existem ainda áreas onde a Internet não só revolucionou os mercados financeiros, como levou à criação de novos mercados, permitindo o acesso desses mercados a novas entidades. Neste contexto, o aparecimento de mercados de negociação de bens e serviços em tempo-real é paradigmático. As bolsas de valores, mercados primários, correctores de apostas, entre outros, viram o seu modelo de funcionamento alterado pela Internet. Estes mercados passaram a negociar em permanência, pelo que, o número de ordens financeiras subiu tão exponencialmente que é actualmente necessário recorrer a complexas plataformas de transações. Hoje em dia existem inúmeras aplicações de negociação em tempo-real para os diversos mercados, umas nativas (domínio de plataformas Microsoft) e outras Web (limitações ao nível de tempo de resposta e das capacidades gráficas). Um aspecto comum a todas elas é o facto de se centrarem na negociação electrónica de ordens emitidas de forma explícita por humanos e ter apenas automatismos para situações de controlo de prejuízo (via triggers). Esta dissertação pretende, por isso, estudar o desenvolvimento de uma nova geração de aplicações de trading que incluam um ambiente de programação embutido na própria aplicação, automação de negociação e backtesting. De forma a colmatar a inexistência deste tipo de aplicações em ambientes não Windows, pretende-se que a mesma seja desenvolvida para ambientes Linux, OSX e Windows.
The Internet brought a revolution to several economic areas because it facilitated the distribution of information and communication between entities. In this context, the emergence of online trading markets of goods and services is paradigmatic. Markets started to negotiate continuously and the number of financial orders rose exponentially as it is currently necessary to employ complex transactions platforms. Today, there are numerous applications of online trading, some are native (limited to platforms such as Microsoft OS), others are Web-based (latency issues). This dissertation presents the development of a new generation of trading applications that includes an embedded programming environment in the application itself, trading automation and backtesting. It was developed as a multi platform application for Linux, OSX and Windows platforms.
23
Maršová, Eliška. "Predikce hodnot v čase." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2016. http://www.nusl.cz/ntk/nusl-255333.
Full textAbstract:
This work deals with the prediction of numerical series whose application is suitable for prediction of stock prices. They explain the procedures for analysis and works with price charts. Also explains the methods of machine learning. Knowledge is used to build a program that finds patterns in numerical series for estimation.
24
Hen, Hsu-Tzu, and 許慈恆. "Automatic Forex Trading Strategies." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/d6pr6v.
Full textAbstract:
碩士大同大學
資訊經營學系(所)
105
Automated trading is one of the major topics in the field of financial domain and has been used wildly. In forex market, buy and sell are the key rules to making profit or loss. The investors always create various technical indicators to generate more benefits. A well-design trading strategy is critical to make money stably in this dramatic foreign exchange market. The investors are usually uncertain about the trading timing and so many factors may influence the investment decision, thus trading automation with a good strategy would be a good way to reduce human mistake and solve investors’ financial problem. In this study, we will focus on homeopathic transactions and fuse multiple indicators to create an effective trading strategy for the currency namely EURUSD. We will launch the trading strategy via the automated system created by the bank of Dukascopy in Europe. Back testing trading period is considered for 10 years (the historic data is provided from Jan. 2004 to Dec. 2013). In addition, the same trading strategy is also launched during the events of Brexit Referendum and American President Election. The results show that this strategy can provide investors with lower risk to adapt the market fluctuations, save time and avoid making the wrong investment decisions in foreign exchange market. Keyword： Forex strategy, Forex indicators, TA (Technical analysis), ATS (Automated trading system),
25
Pereira, Otavio Silva. "Algorithmic Trading Strategies: Automating and Back-testing the Perfect Order Strategy." Master's thesis, 2022. http://hdl.handle.net/10362/135618.
Full textAbstract:
Dissertation presented as the partial requirement for obtaining a Master's degree in Statistics and Information Management, specialization in Risk Analysis and ManagementThe evolution of technology alongside the development of new techniques of algorithmic trading over the past 30 decades (Narang, 2009) allowed global financial markets to achieve higher transaction volume and execution efficiency (Kissell, 2006). In this context, those who fail to adapt to this reality may not survive in financial markets in the future (Chan, 2009). For that, as an attempt to participate in the ongoing automated trading evolution, the present study aims to back-test the Perfect Order Strategy (Lien, 2015) in some selected FX pairs through a fully automated trading system. As a part of the methodology process, the author developed the referred automated trading system through the use of different algorithmic techniques, trading, and risk management models available in the literature, see (Basso, 2019; Leshik & Cralle, 2011; Narang, 2009; Neely et al., 2014; Wilder Jr., 1978). Although the strategy had a positive return at the end of the tests, it performed below the S&P500 index over the same period. Moreover, the results from the back-test showed that the strategy was able to identify trends in its early stages reasonably. In turn, the automated trading system and the advantages that an algorithm execution-based system brought to the strategy played an important role in controlling losses and, therefore, protecting the investment capital. However, the procedures for establishing the stop-loss limit order and the take-profit target showed a flaw and were responsible, in part, for the poor performance of the strategy. Indeed, we are confident that further research in general, particularly in the stop-loss and take-profit target procedures, could improve the strategy's overall performance.
26
Jian, Wen-Zhu, and 簡文助. "The prototyping of an automatic Trading System." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/56049813964950716973.
Full textAbstract:
碩士國立中正大學
資訊管理學系
87
Financial researches or technical analysis traditionally employed the closing prices of equities as their basis for analysis. It is arguable that if the singular closing price can sufficiently represent all the trading prices of an equity in a trading day. This paper made use of the intraday trading data to check if this high frequency data can facilitate us to screen out profitable trades more effectively. The tick-by-tick trade data from NYSE was converted to trade data in three minutes interval to facilitate this study. The data was employed to check if the technical analysis using this intraday data could produce high return. The annual return was booked between 25.5% to 47.1% without transaction cost. The annual return fell in between 5.4% to 36.6% when proper transaction cost was introduced. The return was calculated based on a hypothetical account with $100,000 seeds fund. A trade was carried out when a buy signal was generated and sufficient fund was available in the account. A sell transaction will be carried out when a sell signal is generated. All holdings were liquidated at the end of simulated trading period. An automatic trading system was developed to test this trading strategy using the real data from market. This trading system will issue trading orders to selected Web-based investment simulation sites, such as Final Bell. Buy/Sell trade(s) will be carried out by the trading systems whenever a trading signal is generated.
27
Chou, Chun-Chih, and 周俊志. "An Automatic Trading System and Analysisof Strategies." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/45367440256226958984.
Full textAbstract:
碩士臺灣大學
資訊工程學研究所
96
In this thesis, we implement an automatic trading system and evaluate some trading strategies. Simulated and practical operation can be executed automatically by real-time intraday data. System can capture transaction data provided by the market. It can also be used as a research platform. About the evaluation of strategies, we mainly focus on the profitability aspects and use the daily transaction data of Taiwan''s Weighted Index futures from 1999 to 2007 and the Dow Jones index futures from 1996 to 2007. By back-testing of these data, we analyze several well-known trading strategies such as MA, KD, RSI, MACD, William %R, and so on.
28
Kang, Chia-Chi, and 康嘉琦. "Automatic Price Ranking of E-commerce Trading Impacts 4P in Marketing." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/91464273234955549818.
Full textAbstract:
碩士國立東華大學
國際企業學系
101
Nowadays, most of online sellers still use low price or promotion approaches to attract consumers. However, they don’t realize that with the development of network technology, consumers are now easy to search and compare the product price online. It means that the degree of product’s price transparency on internet is more obvious today. This change will make different impact in pricing and promotion. The purpose of this research is to find out the reason why product’s price transparency could impact pricing and promotion. In this study we finish the survey via questionnaire to people who has online shopping experience. After retrieving the results, we use statistical analysis to verify that whether the price transparency impacts consumers in choice of the price for same product or not? In addition, the promotional activities whether stimulate consumer willingness to purchase product even after product price ranking or not? The result of this study hopes to help enterprises arrange business and promotion strategies to provide and meet the services of consumer’s demand, to promote consumer’s royalty and stimulate the intention of re-purchase for obtaining favorable competitive advantages.
29
Chang, Weichen, and 張維真. "An Automatic Trading Analyze Platform for Portfolio which Construct from Equal Divided Method and Trading Strategy on America Stock Market." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/9dfe65.
Full textAbstract:
碩士國立中央大學
資訊管理學系
107
The development of financial technology helps financial services growing up. How to combine program trading and fundamental analysis is always an issue in public. However, there isn't a complete system for automatic back testing on several fundamental factors with program trading. Also lack of multi-portfolio analysis method. Yun-Chun, Hsieh (2018) has pointed out that using equal divided method based on fundamental factors to analyze stock selection will indeed have greater benefits. This study reconstructs that research to build a scalable portfolio structure, integrate technical and fundamental analysis, back test the performance of multi-portfolio and multi-stock in different markets, and visualize the result of analysis. Provide users a platform for evaluating stocks simply. This system use Amiboker, Python, MySQL, Jupyter Notebook and Plotly to implement the platform and research on the shares of companies listed in New York Stock Exchange from January 1, 1998 to December 31, 2016. Conduct an object-oriented portfolio with technical analysis, fundamental analysis and investment method. Also build a automatic process of back test and analysis by connecting python with program trading software Amibroker. Help users customize the portfolio parameters they focused, and display the results of profit and risk using statistical graphics. The result of the study shows that there are several price momentum factors are highly relevant in rank and profit. When choosing the best group of appropriate fundamental factors as the basic of portfolio can make about 40% compound average growth rate, which means that considering these fundamental factors and other portfolio parameters when selecting stock will have higher benefits.
30
Chou, Chin, and 周慶. "Applying Automatic Deep Learning to Estimate Risk Neutral Density for Option Pricing and Trading." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/96ycn6.
Full textAbstract:
碩士國立交通大學
資訊管理研究所
107
Option pricing has long been researched over the past years. In the past, the estimation of the underlying asset price distribution was usually resolved by statistical and stochastic processes. However, these traditional methods made some strict economic assumptions. These strict assumptions have proven to be inappropriate in past studies. The previous researches have already confirmed that the application of deep learning can correctly deal with option pricing after training with historical transaction data. These models, which are trained from a large amount of knowledge in historical series data, do not require any premise assumptions. Such characteristics allow deep learning models to achieve superior performance in terms of pricing accuracy over traditional models. There are two different methods Based on this idea proposed in this article. The first method inherits the framework of the traditional Black-Scholes model. And by extending its framework to achieve a better pricing result. The second method estimates the underlying asset price distribution by learning the discrete implied distribution first then adjust by the option price directly. The methods proposed in this paper are rolling test on the TAIEX options in 2017. When the rolling test is applied, there is an instability observed that one neural architecture can not deal with all time period. To achieve a more stable result, this article utilizes automatic deep learning techniques, which is called neural architecture search(NAS), and by using the training data as an input to the automatic neural architecture search, different architectures for the different time period can be generated through a single controller. The whole proposed pricing system can generate better pricing results calculated in mean absolute error in 2017. In addition to the pricing results, the pricing model proposed in this article is also used in an options trading strategy, and the model can achieve a better trading performance than the traditional
31
Gouveia, André Nunes Correia. "Machine Learning Applications on Algorithmic Trading in the Foreign Exchange Market." Master's thesis, 2020. http://hdl.handle.net/10362/125436.
Full textAbstract:
Nowadays, the largest share of trades done in market exchanges are made by computers.
This has been proving to be the main way to invest in the various exchanges. Since the
turn of the 20th century, the total volume of trades performed automatically by machines
in the United States stock market as gone up from 15% to around 80%. Similarly, in the
foreign exchange market, the largest market of the world with over 6 trillion US dollars in
daily trade volume during 2019, it is estimated that the large majority of trades are also
made by computers.
With the possibility of using machines to trade for us, it makes sense to consider
a mathematical theory that deals with modeling prices and financial products, and to
program a software to take advantage of this information. Since the last century, another
type of models have also been developed that have the capability of adapting themselves,
or learn, with the information that they are provided.
The objective of this thesis is to implement a strategy that benefits from the information
generated by a machine learning model. This required an in-depth research on the
underlying theory for this type of models, which is carefully defined here. Besides this,
we developed a system that trades automatically for us, including a detailed backtesting
engine that permitted to test this strategy, among others, in a simulated environment
before using it in the market. This automatic trading system was meticulously designed to
ensure extensibility and robustness purposing to explore as many strategies and models as
needed, including machine learning approaches, based on a large set of user configurations.
Subsequently, the foreign exchange market was used to live-run our strategies, which is
open 24h a day during weekdays and is highly liquid. As a benchmark, other more common
strategies were also tested and the predictive capability of the machine learning model was
compared with an established mathematical model, the autoregressive integrated moving
average model.Hoje em dia, a maior parte dos negócios em bolsa são feitos por computadores. Esta tem vindo a provar-se ser a forma principal de investir nas várias bolsas. Desde o virar do século 20, o volume total de negócios feitos por máquinas no mercado de ações dos Estados Unidos aumentou de 15% para cerca de 80%. Da mesma forma, no mercado de câmbio, o maior mercado do mundo com mais de 6 triliões de dólares americanos em volume de negócios diariamente durante 2019, é estimado que a larga maioria do total de negócios seja também feita por computadores. Com a possibilidade de usar máquinas para fazer negócios por nós, faz sentido considerarmos uma teoria matemática que trate de modelar preços e produtos financeiros, e desenvolver um programa que tome partido desta informação. Desde o século passado, tem-se desenvolvido também outro tipo de modelos que têm a capacidade de se adaptar, ou aprender, com a informação que lhes é passada. O objetivo desta dissertação passa por implementar uma estratégia que tome partido da informação gerada por um modelo de aprendizagem automática. Para tal, realizou-se uma pesquisa aprofundada sobre a teoria subjacente a este tipo de modelos, que definimos cuidadosamente aqui. Para além disto, foi desenvolvido um sistema que faz os negócios automaticamente por nós, incluindo um mecanismo de backtesting que permite testar esta estratégia, entre outras, num ambiente simulado antes de a usar no mercado. Este sistema de negociação automático foi projetado meticulosamente para garantir extensibilidade e robustez com o intuito de explorar tantas estratégias e modelos quanto necessárias, incluindo abordagens de aprendizagem automática, baseado num conjunto de configurações definidas pelo utilizador. Subsequentemente, usámos o mercado de câmbio para correr as nossas estratégias ao vivo, que está aberto 24h por dia durante os dias de semana, e é altamente líquido. Como referência, foram também testadas outras estratégias mais comuns e a capacidade preditiva do modelo de aprendizagem automática foi comparado com um modelo matemático estabelecido, o modelo auto-regressivo integrado de médias móveis.
32
ZEMAN, Petr. "Efektivnost trhu a automatické obchodní systémy." Doctoral thesis, 2013. http://www.nusl.cz/ntk/nusl-156660.
Full textAbstract:
The dissertation thesis deals with the problem efficiency of the spot currency market. The main aim of this thesis is to verify the Efficient-market hypothesis on the majo foreign exchange pairs, and especially in the short term. The author focuses on the effective functioning of foreign exchange markets. The behaiour of the five main spot foreign exchange pairs - EUR/USD, GBP/USD, USD/CHF, USD/JPY and USD/CAD was analyzed in the thesis. Due to the increasing rise of intraday trades and growing popularity of margin accounts among retail investors, spot rates have been investigated primarily through a high-frequency data, that were collected for a period equal to or shorter than one day. The hypothesis of the effective exchange rate behaviour was verified by both using statistical methods, such as through automated trading systems, which were designed to assess the economic importance of the theory and to exclude or confirm the possibility of achieving above-average profits of retail investors on the foreign exchange markets.
33
張惠雯. "The Investment Performance of Dollar Cost Averaging with Automatic Trading Rule of Stop-profit and Add-up." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/84085171956609019901.
Full textAbstract:
碩士逢甲大學
金融碩士在職專班
102
This thesis compares through Monte Carlo simulations the investment returns, risk, and performance of a traditional dollar-cost averaging (DCA) strategy with an enhanced DCA strategy. The enhanced DCA strategy is DCA with profit-taking and position-increasing (PTAPI) mechanism. For some mutual funds investment or variable life insurance policies, the appended mechanism can be used by investors with some expenses or free. Thus, it is important to know how the mechanism affects investment results. Unlike a typical DCA which invests regularly on risky assets only, DCA with PTAPI additionally invests on safe assets, like money market funds. When profit-taking happens, some risky assets will be sold to lock in profit and the money will move to money market funds. On the other hand, when position-increasing occurs, some money in the money market funds will move out to increase risky-asset position. A case of DCA with PTAPI in a variable life insurance policy is used for the simulation and comparison. The simulated results show that the average returns of traditional DCA is mostly higher than those of DCA with PTAPI. However, by using standard deviation or value-at-risk as a risk indicator, DCA with PTAPI is less risky than DCA. By calculating the winning chance of 10,000 scenarios, DCA with PTAPI has a greater winner chance if the growth rate of the risky asset is low and the market is volatile. Thus, it is recommended that the PTAPI mechanism is applied with DCA only when the market is volatile and less trending up.
34
Hsieh, Yun-Chun, and 謝昀峻. "The results of verifying an automatic platform utilizing equal divided method and trading strategy on Taiwan stocks." Thesis, 2018. http://ndltd.ncl.edu.tw/handle/q9k6s3.
Full textAbstract:
碩士國立中央大學
資訊管理學系
106
We always concern about how to make profits stably on the stock market. Along with the development of financial technology, it seems no longer out of reach. In the past, most of investment in stocks field focused on stock selection, market timing, profit, risk evaluation and applied a single strategy on a single stock. They lacked of a program trading which make us change strategy and stock easily and it should be more fast, easy to comprehend and also could show more detail information to us. Therefore, this study is dedicated to build an integrated system including stock selection, equal divided method based on fundamental factors, core trading strategies, different ways of investment and number of shares held. We want to combine all of these aspects to analyze and show the result automatically to make users can understand and compare the result simply. The system utilizes Amibroker, Python, MySQL and Django to implement. And it could be divided by several parts including sort ten different fundamental factors, make batch files to allow Amibroker to conduct multi-variables and multi-stock automated backtest and output as csv files. Finally, we can display the results of profit and risk analysis on the Django website. This study research on Taiwan stocks from January 1, 2010 to December 31, 2017. According to different fundamental factors, the stock will be divided into ten parts by using equal divided method. In addition, quarterly reports are used, we’ll re-order all stocks for each season and then decide which part of it should be buy or not. In terms of strategy, we compare Buy and Hold with Keltner Channel, and then with different capital investment methods and the number of shares held for comprehensive comparison to find out what’s the most effective fundamental factors in different configurations. The result of the study shows that there are several fundamental factors that are highly relevant in rank and profit which means that choosing the best group of appropriate fundamental indicators as the basic of portfolio will indeed have greater benefits. Beside, come with proper Keltner Channle will make greater net profit and reduce the maximum drawdown effectively. In addition, the study provides a framework and process to make it easily in the future if we want to add a new fundamental indicator, strategy, investment method, etc., we can easily apply to this system and complete the analysis.
35
YEOH, WEI-LUN, and 楊偉倫. "Automatic Stock Trading System Combined with Short Selling and Stop Loss Using Multiple Moving Averages and EGQTS Algorithm." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/9pbbey.
Full textAbstract:
碩士國立暨南國際大學
資訊工程學系
107
This research proposes a novel dynamic trading system utilizing only one simple but common technical indicator, the moving average (MA), albeit in a way which differs from traditional methods. We also analyze the weight moving average (WMA) and exponential moving average (EMA), which has the multiplying factor of MA. In addition, a modified evolutionary algorithm, the globe best-guide quantum-inspired tabu search algorithm (GQTS), was created to quickly and stably search for the optimal combination of MA parameters. In order to avoid the overfitting problem, this approach applied the sliding window, and raised the 2-phase sliding window and year-on-year training period to address more comprehensive stock trading problems. In addition to normal stock trading, this system adopts another legal trading method, short selling. The experiment results reveal that our method has a greatly improved MA ability. The result indicates that the WMA always has the best performance in four different targets. The sliding window period with 2-phase and year-on-year can improve the performance of the trading system. When the trading system adopts short selling it can significantly improve investment profit.
36
Осіпова, Юлія Володимирівна. "Програмна реалізація автоматизації здійснення торгових операцій на біржі цінних паперів." Магістерська робота, 2020. https://dspace.znu.edu.ua/jspui/handle/12345/2256.
Full textAbstract:
Осіпова Ю. В. Програмна реалізація автоматизації здійснення торгових операцій на біржі цінних паперів : кваліфікаційна робота магістра спеціальності 122 "Комп'ютерні науки" / наук. керівник К. С. Решевська. Запоріжжя : ЗНУ, 2020. 58 с.UA : Робота викладена на 58 сторінках друкованого тексту, містить 1 таблицю, 3 рисунки, 17 джерел. Об’єкт дослідження – процеси біржової торгівлі на ринку фінансів і цінних паперів. Мета роботи: дослідження методів розробки та реалізація програмного продукту (торгового радника) засобами Python. Методи дослідження – аналітичний, порівняльний. Торгівля на біржі фінансів і цінних паперів в Україні набрала величезної популярності за останні роки. Це пов'язане зі зростанням можливостей обробки і розповсюдження фінансової інформації, завдяки чому фінансова торгівля стала більш досяжною для фізичних і юридичних осіб. В умовах зростання обсягів операцій, збільшення кількості гравців, скорочення часу розповсюдження інформації і здійснення угод, надзвичайно зростає попит на автоматизовані технології технічного аналізу стану ринку, які дозволяють проводити поглиблений аналіз ринкових показників, контролювати і мінімізувати торговельні ризики, забезпечуючи зменшення фінансових втрат. В роботі викладені: а) основні поняття фондового ринку. Розглянуті форми, стилі і методи біржової торгівлі; б) аналіз існуючих торгових платформ та біржових торгівельних роботів; в) програмна реалізація торгового робота засобами Рython.
EN : The work is presented on 58 pages of printed text, 1 table, 3 figures, 17 references. The object of study is the processes of stock exchange trading in the financial and securities markets. The aim of the study is study methods of development and implementation of software (trading advisor) by Python tools. The methods of research are analytical, comparative. Trading on the stock exchange of finance and securities in Ukraine has gained enormous popularity in recent years. This is due to the increased ability to process and disseminate financial information, making financial trading more accessible to individuals and businesses. As operations grow, the number of players increases, the dissemination of information and the execution of transactions, the demand for automated market analysis technologies that allow for an in-depth analysis of market indicators, control and minimize trade risks while reducing financial losses is growing. The work outlines: a) basic concepts of the stock market. Forms, styles and methods of exchange trading are considered; b) analysis of existing trading platforms and stock trading robots; c) Python software implementation of trading robot.
37
Pinho, João Almeida Rangel. "As corretoras online e os desafios de tributação inerentes à digitalização da economia." Master's thesis, 2020. http://hdl.handle.net/10400.14/33719.
Full textAbstract:
A Digitalização da Economia representa um desafio acrescido para a soberania dos Estados devido à crescente perda de receita fiscal associada a uma obsolescência de determinados conceitos fiscais concebidos para um modelo de empresa tradicional que pressupõe a existência de um estabelecimento estável mediante o qual realizam as suas operações. A nossa dissertação foca-se nos serviços de investimento prestados remotamente pelas corretoras online independentes fazendo alusão à controvérsia instalada pelas dificuldades de tributação com o advento do comércio eletrónico, sem descurar a apreciação das soluções propostas pela OCDE e UE para a Economia Digital. Contudo, as soluções, além de complexas, são meras recomendações que não conseguem gerar o consenso no seio da comunidade internacional. Assumimos, por isso, o carácter urgente da adaptação do conceito estabelecimento estável à presença digital significativa proposta pelo BEPS para efeitos de imputação dos lucros gerados à jurisdição onde efetivamente é criado valor.The digitalization of the economy represents an added challenge for the sovereignty of States due to the growing loss of tax revenue associated with the obsolescence of certain tax concepts designed for a traditional business model that presupposes the existence of a stable establishment through which they carry out their operations. Our dissertation focuses on the investment services provided remotely by independent online brokers alluding to the controversy installed by the difficulties of taxation with the advent of e-commerce, without neglecting the appreciation of the solutions proposed by the OECD and EU for the Digital Economy. However, the solutions, besides being complex, are mere recommendations that fail to generate consensus within the international community. We therefore assume the urgent nature of adapting the concept of stable establishment to the significant digital presence proposed by BEPS for the purpose of allocating the profits generated to the jurisdiction where value is effectively created.