Portfolio Optimization via Transfer Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Kexin, Zhang, Xiaomeng, Zhang, Xinyu
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918218740793344
author Wang, Kexin
Zhang, Xiaomeng
Zhang, Xinyu
author_facet Wang, Kexin
Zhang, Xiaomeng
Zhang, Xinyu
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21221
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Portfolio Optimization via Transfer Learning
Wang, Kexin
Zhang, Xiaomeng
Zhang, Xinyu
Portfolio Management
Applications
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.
title Portfolio Optimization via Transfer Learning
topic Portfolio Management
Applications
url https://arxiv.org/abs/2511.21221