Building portfolios based on machine learning predictions
Bibliographic Data
| ID | 15066557 |
|---|---|
| Authors | Tomasz Kaczmarek (0000-0001-6138-5280, Poznań University of Economics and Business, corresponding author), Katarzyna Perez (0000-0003-3331-8456, Poznań University of Economics and Business) |
| Year | 2022 |
| Volume | 35 |
| Issue | 1 |
| Pages | 19-37 |
| Publication date | 2022-12-31 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Economic Research-Ekonomska Istraživanja (JOURNAL) |
| Journal identifiers | ISSN: 1331-677X • E-ISSN: 1848-9664 |
| Publisher | Informa UK Limited (PUBLISHER • GB) |
| DOI | 10.1080/1331677x.2021.1875865 |
| OpenAlex | W3126338114 |
| Language | EN |
| References cited | 32 |
This paper demonstrates that portfolio optimization techniques represented by Markowitz mean-variance and Hierarchical Risk Parity (HRP) optimizers increase the risk-adjusted return of portfolios built with stocks preselected with a machine learning tool. We apply the random forest method to predict the cross-section of expected excess returns and choose n stocks with the highest monthly predictions. We compare three different techniques—mean-variance, HRP, and 1/N— for portfolio weight creation using returns of stocks from the S&P500 and STOXX600 for robustness. The out-of-sample results show that both mean-variance and HRP optimizers outperform the 1/N rule. This conclusion is in the opposition to a common criticism of optimizers’ efficiency and presents a new light on their potential practical usage
JavaScript · Programming language · Zoom · Computer Science · Engineering · Financial Markets and Investment Strategies · Forecasting Techniques and Applications · Stock Market Forecasting Methods · Artificial Intelligence
| Highly cited | No |
|---|