Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning
With the advances in time-series prediction, several recent developments in machine learning have shown that integrating prediction methods into portfolio selection is a great opportunity. In this paper, we propose a novel approach to portfolio formation strategy based on a hybrid machine learning m...
| Main Authors: | , |
|---|---|
| Formato: | Artigo |
| Idioma: | English |
| Publicado em: |
MDPI AG
2022-08-01
|
| Colecção: | International Journal of Financial Studies |
| Assuntos: | |
| Acesso em linha: | https://www.mdpi.com/2227-7072/10/3/64 |
| _version_ | 1827262919506657280 |
|---|---|
| author | Apichat Chaweewanchon Rujira Chaysiri |
| author_facet | Apichat Chaweewanchon Rujira Chaysiri |
| author_sort | Apichat Chaweewanchon |
| collection | DOAJ |
| description | With the advances in time-series prediction, several recent developments in machine learning have shown that integrating prediction methods into portfolio selection is a great opportunity. In this paper, we propose a novel approach to portfolio formation strategy based on a hybrid machine learning model that combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) with robust input features obtained from Huber’s location for stock prediction and the Markowitz mean-variance (MV) model for optimal portfolio construction. Specifically, this study first applies a prediction method for stock preselection to ensure high-quality stock inputs for portfolio formation. Then, the predicted results are integrated into the MV model. To comprehensively demonstrate the superiority of the proposed model, we used two portfolio models, the MV model and the equal-weight portfolio (1/N) model, with LSTM, BiLSTM, and CNN-BiLSTM, and employed them as benchmarks. Between January 2015 and December 2020, historical data from the Stock Exchange of Thailand 50 Index (SET50) were collected for the study. The experiment shows that integrating preselection of stocks can improve MV performance, and the results of the proposed method show that they outperform comparison models in terms of Sharpe ratio, mean return, and risk. |
| first_indexed | 2024-04-11T11:22:28Z |
| format | Article |
| id | doaj.art-35bac5c273354a9584fb2cf6f4a2fd5f |
| institution | Directory Open Access Journal |
| issn | 2227-7072 |
| language | English |
| last_indexed | 2025-03-22T03:21:55Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | International Journal of Financial Studies |
| spelling | doaj.art-35bac5c273354a9584fb2cf6f4a2fd5f2024-04-29T18:14:36ZengMDPI AGInternational Journal of Financial Studies2227-70722022-08-011036410.3390/ijfs10030064Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine LearningApichat Chaweewanchon0Rujira Chaysiri1School of Management Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandSchool of Management Technology, Sirindhorn International Institute of Technology, Thammasat University, Pathum Thani 12120, ThailandWith the advances in time-series prediction, several recent developments in machine learning have shown that integrating prediction methods into portfolio selection is a great opportunity. In this paper, we propose a novel approach to portfolio formation strategy based on a hybrid machine learning model that combines convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) with robust input features obtained from Huber’s location for stock prediction and the Markowitz mean-variance (MV) model for optimal portfolio construction. Specifically, this study first applies a prediction method for stock preselection to ensure high-quality stock inputs for portfolio formation. Then, the predicted results are integrated into the MV model. To comprehensively demonstrate the superiority of the proposed model, we used two portfolio models, the MV model and the equal-weight portfolio (1/N) model, with LSTM, BiLSTM, and CNN-BiLSTM, and employed them as benchmarks. Between January 2015 and December 2020, historical data from the Stock Exchange of Thailand 50 Index (SET50) were collected for the study. The experiment shows that integrating preselection of stocks can improve MV performance, and the results of the proposed method show that they outperform comparison models in terms of Sharpe ratio, mean return, and risk.https://www.mdpi.com/2227-7072/10/3/64portfolio optimizationmean-variance modelstock predictionstock selectionmachine learning |
| spellingShingle | Apichat Chaweewanchon Rujira Chaysiri Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning International Journal of Financial Studies portfolio optimization mean-variance model stock prediction stock selection machine learning |
| title | Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning |
| title_full | Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning |
| title_fullStr | Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning |
| title_full_unstemmed | Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning |
| title_short | Markowitz Mean-Variance Portfolio Optimization with Predictive Stock Selection Using Machine Learning |
| title_sort | markowitz mean variance portfolio optimization with predictive stock selection using machine learning |
| topic | portfolio optimization mean-variance model stock prediction stock selection machine learning |
| url | https://www.mdpi.com/2227-7072/10/3/64 |
| work_keys_str_mv | AT apichatchaweewanchon markowitzmeanvarianceportfoliooptimizationwithpredictivestockselectionusingmachinelearning AT rujirachaysiri markowitzmeanvarianceportfoliooptimizationwithpredictivestockselectionusingmachinelearning |