News spreads rapidly across languages and regions, but translations may lose subtle nuances. We propose a method to align sentences in multilingual news articles using optimal transport, identifying semantically similar content across languages. We apply this method to align more than 140,000 pairs of Bloomberg English and Japanese news articles covering around 3500 stocks in Tokyo exchange over 2012-2024. Aligned sentences are sparser, more interpretable, and exhibit higher semantic similarity. Return scores constructed from aligned sentences show stronger correlations with realized stock returns, and long-short trading strategies based on these alignments achieve 10\% higher Sharpe ratios than analyzing the full text sample.
@article{arxiv.2510.19203,
title = {Aligning Multilingual News for Stock Return Prediction},
author = {Yuntao Wu and Lynn Tao and Ing-Haw Cheng and Charles Martineau and Yoshio Nozawa and John Hull and Andreas Veneris},
journal= {arXiv preprint arXiv:2510.19203},
year = {2025}
}
Comments
6 pages, 4 tables, 2 figures, AI for Finance Symposium'25 Workshop at ICAIF'25