Building portfolios based on machine learning predictions. Kaczmarek, T. & Perez, K. Economic Research-Ekonomska Istraživanja, 35(1):19–37, December, 2022. 8 citations (Semantic Scholar/DOI) [2023-06-19]Paper doi abstract bibtex 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.
@article{kaczmarek_building_2022,
title = {Building portfolios based on machine learning predictions},
volume = {35},
issn = {1331-677X, 1848-9664},
url = {https://www.tandfonline.com/doi/full/10.1080/1331677X.2021.1875865},
doi = {10.1080/1331677X.2021.1875865},
abstract = {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.},
language = {en},
number = {1},
urldate = {2023-06-17},
journal = {Economic Research-Ekonomska Istraživanja},
author = {Kaczmarek, Tomasz and Perez, Katarzyna},
month = dec,
year = {2022},
note = {8 citations (Semantic Scholar/DOI) [2023-06-19]},
keywords = {/unread},
pages = {19--37},
}
Downloads: 0
{"_id":"LvADrGujS5jCXmXwB","bibbaseid":"kaczmarek-perez-buildingportfoliosbasedonmachinelearningpredictions-2022","author_short":["Kaczmarek, T.","Perez, K."],"bibdata":{"bibtype":"article","type":"article","title":"Building portfolios based on machine learning predictions","volume":"35","issn":"1331-677X, 1848-9664","url":"https://www.tandfonline.com/doi/full/10.1080/1331677X.2021.1875865","doi":"10.1080/1331677X.2021.1875865","abstract":"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.","language":"en","number":"1","urldate":"2023-06-17","journal":"Economic Research-Ekonomska Istraživanja","author":[{"propositions":[],"lastnames":["Kaczmarek"],"firstnames":["Tomasz"],"suffixes":[]},{"propositions":[],"lastnames":["Perez"],"firstnames":["Katarzyna"],"suffixes":[]}],"month":"December","year":"2022","note":"8 citations (Semantic Scholar/DOI) [2023-06-19]","keywords":"/unread","pages":"19–37","bibtex":"@article{kaczmarek_building_2022,\n\ttitle = {Building portfolios based on machine learning predictions},\n\tvolume = {35},\n\tissn = {1331-677X, 1848-9664},\n\turl = {https://www.tandfonline.com/doi/full/10.1080/1331677X.2021.1875865},\n\tdoi = {10.1080/1331677X.2021.1875865},\n\tabstract = {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.},\n\tlanguage = {en},\n\tnumber = {1},\n\turldate = {2023-06-17},\n\tjournal = {Economic Research-Ekonomska Istraživanja},\n\tauthor = {Kaczmarek, Tomasz and Perez, Katarzyna},\n\tmonth = dec,\n\tyear = {2022},\n\tnote = {8 citations (Semantic Scholar/DOI) [2023-06-19]},\n\tkeywords = {/unread},\n\tpages = {19--37},\n}\n\n","author_short":["Kaczmarek, T.","Perez, K."],"key":"kaczmarek_building_2022","id":"kaczmarek_building_2022","bibbaseid":"kaczmarek-perez-buildingportfoliosbasedonmachinelearningpredictions-2022","role":"author","urls":{"Paper":"https://www.tandfonline.com/doi/full/10.1080/1331677X.2021.1875865"},"keyword":["/unread"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/victorjhu","dataSources":["CmHEoydhafhbkXXt5"],"keywords":["/unread"],"search_terms":["building","portfolios","based","machine","learning","predictions","kaczmarek","perez"],"title":"Building portfolios based on machine learning predictions","year":2022}