Machine learning classification outperforms regression in portfolio construction

A research paper published on arXiv explores the effectiveness of machine learning models in portfolio construction, finding that classification models outperform regression models. The study demonstrates that a stacked ensemble of gradient boosted trees, random forests, and neural networks achieved a significantly higher Sharpe ratio using classification compared to regression. This advantage is attributed to classification's superior ability to separate return deciles, retaining economically large alphas even after accounting for regression-based methods. AI

IMPACT Classification models in machine learning offer superior performance for portfolio construction compared to regression, potentially leading to more effective investment strategies.

RANK_REASON Research paper published on arXiv detailing findings on machine learning models. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.LG →

• Neural network
• arXiv
• Classification
• Machine Learning
• Random forest
• Sharpe ratio
• Yang Bai

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →