Aligning Multilingual News for Stock Return Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914107629764608 |
|---|---|
| author | Wu, Yuntao Tao, Lynn Cheng, Ing-Haw Martineau, Charles Nozawa, Yoshio Hull, John Veneris, Andreas |
| author_facet | Wu, Yuntao Tao, Lynn Cheng, Ing-Haw Martineau, Charles Nozawa, Yoshio Hull, John Veneris, Andreas |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_19203 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Aligning Multilingual News for Stock Return Prediction Wu, Yuntao Tao, Lynn Cheng, Ing-Haw Martineau, Charles Nozawa, Yoshio Hull, John Veneris, Andreas Computational Finance Computation and Language J.4; I.2.7 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. |
| title | Aligning Multilingual News for Stock Return Prediction |
| topic | Computational Finance Computation and Language J.4; I.2.7 |
| url | https://arxiv.org/abs/2510.19203 |