Aligning Multilingual News for Stock Return Prediction
This work addresses the challenge of leveraging multilingual news for financial forecasting, offering incremental improvements in stock return prediction for investors and analysts.
The paper tackled the problem of aligning multilingual news articles for stock return prediction by using optimal transport to identify semantically similar content across languages, resulting in aligned sentences that improved trading strategies with a 10% higher Sharpe ratio compared to full text analysis.
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.