A Universal End-to-End Approach to Portfolio Optimization via Deep Learning

TL;DR

This paper introduces a universal deep learning framework for portfolio optimization that directly predicts asset distributions, bypassing traditional forecasting and covariance estimation, and handles various constraints and objectives.

Contribution

It presents a novel end-to-end neural network approach that generalizes portfolio optimization, accommodating multiple objectives and constraints without relying on classical predictive steps.

Findings

Outperforms classical methods on synthetic data.

Effective on real-world data with hundreds of instruments.

Robust across different objective functions and constraints.

Abstract

We propose a universal end-to-end framework for portfolio optimization where asset distributions are directly obtained. The designed framework circumvents the traditional forecasting step and avoids the estimation of the covariance matrix, lifting the bottleneck for generalizing to a large amount of instruments. Our framework has the flexibility of optimizing various objective functions including Sharpe ratio, mean-variance trade-off etc. Further, we allow for short selling and study several constraints attached to objective functions. In particular, we consider cardinality, maximum position for individual instrument and leverage. These constraints are formulated into objective functions by utilizing several neural layers and gradient ascent can be adopted for optimization. To ensure the robustness of our framework, we test our methods on two datasets. Firstly, we look at a synthetic dataset where we demonstrate that weights obtained from our end-to-end approach are better than classical predictive methods. Secondly, we apply our framework on a real-life dataset with historical observations of hundreds of instruments with a testing period of more than 20 years.