Loading...

Applying Machine Learning Algorithms in Stock Market Forecasting Using Transactional Data

Hosseini, Amir Reza | 2023

49 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 56258 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Akhavan Niaki, Taghi
  7. Abstract:
  8. Research in the field of financial market prediction has always been an intriguing subject for academic researchers and stock traders, despite its associated complexities and challenges. Accurately forecasting stock prices and market indices is considered a complex task due to their nonlinear and dynamic nature, requiring analysis of intricate time series data. Over time, various models such as regression models, classification methods, statistical techniques, and artificial intelligence algorithms have been used to predict these variables. With the advancement of technology and the development of AI-based models, particularly machine learning models, along with the availability of vast amounts of data in the stock market, these models and algorithms have become widely utilized in this domain. Additionally, with the advancement of information technology infrastructure, supplementary data sources such as traders' payment information have been leveraged to improve predictions. In this research, the focus is on predicting the Tehran Stock Exchange's overall market index within a daily time frame using data related to the amounts deposited by brokers into retail traders' wallets in the Tehran Stock Exchange trading panel. Machine learning algorithms are employed for this purpose. The performance of these models is evaluated using metrics such as accuracy and other commonly used criteria in the literature for assessing classification algorithms. To enhance prediction accuracy and consider the strengths and weaknesses of the algorithms, a voting system is implemented to maximize the quality of predictions. Furthermore, a simulated intelligent trading system based on these algorithms outperforms the returns of the overall market index. Machine learning algorithms and deep learning techniques such as logistic regression, random forest, support vector machines, artificial neural networks, and other algorithms are used in this research
  9. Keywords:
  10. Machine Learning ; Tehran Stock Exchange ; Market Prediction ; Stock Market ; Trading Systems ; Brockerages Payment Transactions

 Digital Object List

 Bookmark

No TOC