Fundamental, Sentiment and Technical analysis for Algorithmic Trading using Novel Genetic Programming algorithms

Created by W.Langdon from gp-bibliography.bib Revision:1.8010

@PhdThesis{Christodoulaki:thesis,

• author = "Evangelia Paraskevi Christodoulaki",
• title = "Fundamental, Sentiment and Technical analysis for Algorithmic Trading using Novel Genetic Programming algorithms",
• school = "School of Computer Science and Electronic Engineering, University of Essex",
• year = "2024",
• address = "UK",
• month = jan,
• keywords = "genetic algorithms, genetic programming",
• URL = "http://kampouridis.net/papers/Eva_PhdThesis_with_template.pdf",
• size = "231 pages",
• abstract = "This thesis explores genetic programming (GP) applications in algorithmic trading, addressing significant advancements in the field. Investors typically rely on fundamental analysis (FA) or technical analysis (TA) indicators, with sentiment analysis (SA) gaining recent attention. Consequently, algorithms have become the primary method for developing pre-programmed trading strategies, leading to substantial financial benefits. While each analysis type has been studied individually, their combined exploration remains limited. Our motivation is to assess if integrating FA, SA, and TA indicators can improve financial profitability. Thus, in Chapter 5, we introduce a novel GP algorithm which combines the three analysis types within the same GP structure, wanting to understand the advantages of their combination. Chapter 6 presents a strongly-typed GP architecture, where each branch of the algorithm represents one analysis type, facilitating improved exploration and exploitation. Furthermore, we showcase a novel fitness function that rewards a tree trading performance and the performance of its FA, SA,and TA subtrees. Chapter 7 aims to enhance the GP algorithm performance and increase the individuals financial advantages. Therefore, we propose a novel GP operator that encourages active trading by injecting trees into the GP population that perform a high number of trades while achieving high profitability at low risk. To evaluate our GP variants performance, we conduct experiments on stocks of 42 international companies, comparing the novel algorithm with the GP variants introduced in the same chapter. Moreover, in Chapters 5 and 6, we compare the proposed GP algorithm against four machine learning benchmarks and a financial trading strategy, while Chapter 7 focuses on comparing the novel GP algorithm exclusively with GP benchmarks. The evaluation employs three financial metrics: Sharpe ratio, rate of return, and risk. Results consistently show that the proposed GP algorithms in each chapter enhance the financial performance of trading strategies, surpassing the benchmarks",
• notes = "supervisor: Michael Kampouridis",

}

Genetic Programming entries for Eva Christodoulaki

Citations