Decision by Supervised Learning with Deep Ensembles: A Practical Framework for Robust Portfolio Optimization
This work addresses portfolio optimization for financial practitioners, offering a practical framework that is incremental in combining supervised learning with ensemble methods.
The paper tackles robust portfolio optimization by proposing Decision by Supervised Learning (DSL), a framework that reframes portfolio construction as a supervised learning problem and uses Deep Ensembles to reduce variance, resulting in superior performance with higher median returns and more stable risk-adjusted metrics compared to traditional and machine learning-based methods.
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.