Machine learning prediction of stock price behavior in SGX
In recent years, ML has been used to solve many complex mathematical problems. Researchers have identified ML as a means to predict stock prices and their characteristics to execute profitable trades in the stock market. This project proposes a novel labelling scheme and evaluates the use of five...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/149323 |
| _version_ | 1826122883373465600 |
|---|---|
| author | Pan, Sun Wei |
| author2 | Wong Jia Yiing, Patricia |
| author_facet | Wong Jia Yiing, Patricia Pan, Sun Wei |
| author_sort | Pan, Sun Wei |
| collection | NTU |
| description | In recent years, ML has been used to solve many complex mathematical problems.
Researchers have identified ML as a means to predict stock prices and their characteristics
to execute profitable trades in the stock market. This project proposes a novel labelling
scheme and evaluates the use of five different ML models, three different feature sets, and
two labelling techniques in predicting stock price characteristics within SGX. Our project
also examines the tuning of each model and the relations between feature sets and labels.
We run our resulting models’ predictions through a backtesting algorithm to evaluate its
real-world application. Our experimentation shows that ML predictions can result in
profitable trading strategies in the SGX, with the AdaBoost, OHLCV, and our novel threeclass labelling combination offering the highest profitability. |
| first_indexed | 2024-10-01T05:55:30Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/149323 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:55:30Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1493232023-07-07T18:11:02Z Machine learning prediction of stock price behavior in SGX Pan, Sun Wei Wong Jia Yiing, Patricia School of Electrical and Electronic Engineering EJYWong@ntu.edu.sg Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Business::Finance::Stock exchanges In recent years, ML has been used to solve many complex mathematical problems. Researchers have identified ML as a means to predict stock prices and their characteristics to execute profitable trades in the stock market. This project proposes a novel labelling scheme and evaluates the use of five different ML models, three different feature sets, and two labelling techniques in predicting stock price characteristics within SGX. Our project also examines the tuning of each model and the relations between feature sets and labels. We run our resulting models’ predictions through a backtesting algorithm to evaluate its real-world application. Our experimentation shows that ML predictions can result in profitable trading strategies in the SGX, with the AdaBoost, OHLCV, and our novel threeclass labelling combination offering the highest profitability. Bachelor of Engineering (Electrical and Electronic Engineering) 2021-05-30T07:28:33Z 2021-05-30T07:28:33Z 2021 Final Year Project (FYP) Pan, S. W. (2021). Machine learning prediction of stock price behavior in SGX. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/149323 https://hdl.handle.net/10356/149323 en A1174-201 application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Business::Finance::Stock exchanges Pan, Sun Wei Machine learning prediction of stock price behavior in SGX |
| title | Machine learning prediction of stock price behavior in SGX |
| title_full | Machine learning prediction of stock price behavior in SGX |
| title_fullStr | Machine learning prediction of stock price behavior in SGX |
| title_full_unstemmed | Machine learning prediction of stock price behavior in SGX |
| title_short | Machine learning prediction of stock price behavior in SGX |
| title_sort | machine learning prediction of stock price behavior in sgx |
| topic | Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence Business::Finance::Stock exchanges |
| url | https://hdl.handle.net/10356/149323 |
| work_keys_str_mv | AT pansunwei machinelearningpredictionofstockpricebehaviorinsgx |