Aligning Multilingual News for Stock Return Prediction

TL;DR

This paper introduces a novel optimal transport-based method for aligning multilingual news sentences, improving interpretability and correlation with stock returns, and enhancing trading strategies.

Contribution

It presents a new approach to align multilingual news using optimal transport, leading to better semantic matching and financial prediction accuracy.

Findings

Aligned sentences are more interpretable and semantically similar.

Return scores from aligned sentences correlate better with stock returns.

Trading strategies based on alignments outperform full-text analysis by 10% in Sharpe ratio.

Abstract

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.