Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918164389953536 |
|---|---|
| author | Kim, Juhyeong Choi, Sungyoon Lee, Youngbin Kim, Yejin Choi, Yongmin Lee, Yongjae |
| author_facet | Kim, Juhyeong Choi, Sungyoon Lee, Youngbin Kim, Yejin Choi, Yongmin Lee, Yongjae |
| contents | We propose Decision by Supervised Learning (DSL), a practical framework for robust portfolio optimization. DSL reframes portfolio construction as a supervised learning problem: models are trained to predict optimal portfolio weights, using cross-entropy loss and portfolios constructed by maximizing the Sharpe or Sortino ratio. To further enhance stability and reliability, DSL employs Deep Ensemble methods, substantially reducing variance in portfolio allocations. Through comprehensive backtesting across diverse market universes and neural architectures, shows superior performance compared to both traditional strategies and leading machine learning-based methods, including Prediction-Focused Learning and End-to-End Learning. We show that increasing the ensemble size leads to higher median returns and more stable risk-adjusted performance. The code is available at https://github.com/DSLwDE/DSLwDE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_13544 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization Kim, Juhyeong Choi, Sungyoon Lee, Youngbin Kim, Yejin Choi, Yongmin Lee, Yongjae Machine Learning Computational Finance Portfolio Management We propose Decision by Supervised Learning (DSL), a practical framework for robust portfolio optimization. DSL reframes portfolio construction as a supervised learning problem: models are trained to predict optimal portfolio weights, using cross-entropy loss and portfolios constructed by maximizing the Sharpe or Sortino ratio. To further enhance stability and reliability, DSL employs Deep Ensemble methods, substantially reducing variance in portfolio allocations. Through comprehensive backtesting across diverse market universes and neural architectures, shows superior performance compared to both traditional strategies and leading machine learning-based methods, including Prediction-Focused Learning and End-to-End Learning. We show that increasing the ensemble size leads to higher median returns and more stable risk-adjusted performance. The code is available at https://github.com/DSLwDE/DSLwDE. |
| title | Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization |
| topic | Machine Learning Computational Finance Portfolio Management |
| url | https://arxiv.org/abs/2503.13544 |