Designing an automated trading bot for strategic order execution
SONAR|HES-SO
- Antelo Cortegana, Antonio
- Anagnostopoulos, Grigorios G. (Degree supervisor)
- Genève : Haute école de gestion de Genève
62 p.
Bachelor of Science HES-SO en Informatique de gestion: Haute école de gestion de Genève, 2024
English
This thesis explores the field of trading with the main objective of designing an automated trading bot that is theoretically able of executing strategic orders. The project uses a multilayer perceptron (MLP) neural network to predict future price movements of a stock, based on historical data. However, the model has not yet reached a level of accuracy sufficient for a deployment in real life.
The data used to train the model includes price history of the stock in the form of Open, High, Low and Close (OHLC) enriched by four technical indicators (EMA, MACD, RSI and VWAP) to improve prediction accuracy as much as possible. Although the project is limited to analysis and simulation on historical data, it provides a solid foundation for the creation of a trading bot. The thesis also includes a comparison with baseline strategies to analyze the model’s performance in simulated trading.
The different sections cover a review of key trading concepts, including a part on Swiss legislation, as well as the development of an automated trading strategy
As English is not my native language, I found writing my Bachelor thesis quite challenging. Therefore, I would like to express my gratitude to my former colleague and friend, Mrs. Deborah Gottlieb, for the time she dedicated to reviewing my work. Her insightful comments on my English and her constructive feedback on my topic were incredibly helpful.
Lastly, I would also like to thank my family and close friends for always believing in me and for their constant support and encouragement, especially during the times when I struggled with motivation. A special thanks to my sister Natalia Antelo Cortegana for her endless patience in reviewing and providing feedback on my work multiple times.
I also utilized modern technologies to support my work. Github Copilot was used to assist in writing code efficiently, while ChatGPT provided valuable help in refining some of the English phrasing. These tools were employed thoughtfully, ensuring that the integrity of the work remained my own.
The data used to train the model includes price history of the stock in the form of Open, High, Low and Close (OHLC) enriched by four technical indicators (EMA, MACD, RSI and VWAP) to improve prediction accuracy as much as possible. Although the project is limited to analysis and simulation on historical data, it provides a solid foundation for the creation of a trading bot. The thesis also includes a comparison with baseline strategies to analyze the model’s performance in simulated trading.
The different sections cover a review of key trading concepts, including a part on Swiss legislation, as well as the development of an automated trading strategy
As English is not my native language, I found writing my Bachelor thesis quite challenging. Therefore, I would like to express my gratitude to my former colleague and friend, Mrs. Deborah Gottlieb, for the time she dedicated to reviewing my work. Her insightful comments on my English and her constructive feedback on my topic were incredibly helpful.
Lastly, I would also like to thank my family and close friends for always believing in me and for their constant support and encouragement, especially during the times when I struggled with motivation. A special thanks to my sister Natalia Antelo Cortegana for her endless patience in reviewing and providing feedback on my work multiple times.
I also utilized modern technologies to support my work. Github Copilot was used to assist in writing code efficiently, while ChatGPT provided valuable help in refining some of the English phrasing. These tools were employed thoughtfully, ensuring that the integrity of the work remained my own.
- Language
-
- English
- Classification
- Computer science and technology
- Notes
-
- Haute école de gestion Genève
- Informatique de gestion
- hesso:hegge
- Persistent URL
- https://sonar.rero.ch/global/documents/331152
Statistics
Document views: 9
File downloads:
- Antelo-Antonio.pdf: 48