Portfolio Optimization via Transfer Learning

2025-11-26

AI Summary

This paper addresses the problem of enhancing portfolio performance in a target market by leveraging cross-market information. We propose a transfer learning framework that asymptotically identifies effective information sources: it dynamically selects and fuses asset return features from multiple markets via forward validation, adaptively absorbing beneficial signals and suppressing spurious ones in a statistically principled manner to achieve asymptotic Sharpe ratio optimality. The method integrates transfer learning, rolling statistical testing, and dynamic weight adjustment—without relying on subjective prior assumptions or strong stationarity requirements. Empirical results demonstrate significant improvements in risk-adjusted returns for both A-share/H-share dual-listed stocks and U.S. multi-sector equity portfolios, with robust cross-market generalizability. Our key contribution is the first theoretically grounded (asymptotically optimal) and practically viable cross-market transfer investment framework that dispenses with stringent stationarity assumptions.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Economics, Online Markets and Human Computation: The sharing economy
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Recognizing that asset markets generally exhibit shared informational characteristics, we develop a portfolio strategy based on transfer learning that leverages cross-market information to enhance the investment performance in the market of interest by forward validation. Our strategy asymptotically identifies and utilizes the informative datasets, selectively incorporating valid information while discarding the misleading information. This enables our strategy to achieve the maximum Sharpe ratio asymptotically. The promising performance is demonstrated by numerical studies and case studies of two portfolios: one consisting of stocks dual-listed in A-shares and H-shares, and another comprising equities from various industries of the United States.

Problem

• Portfolio optimization using cross-market transfer learning
• Asymptotically achieving maximum Sharpe ratio performance
• Selectively incorporating valid information while discarding misleading data

Innovation

• Uses transfer learning for cross-market information
• Asymptotically identifies and utilizes informative datasets
• Achieves maximum Sharpe ratio through forward validation