News-Driven Stock Prediction With Attention-Based Noisy Recurrent State Transition

TL;DR

This paper introduces an attention-based recurrent model that explicitly separates news effects from noise to improve stock movement prediction, offering better accuracy and explainability.

Contribution

It is the first to explicitly model both news events and noise over stock value states for prediction tasks.

Findings

Model outperforms strong baselines

Uses attention for explainability

Separates news effects from noise

Abstract

We consider direct modeling of underlying stock value movement sequences over time in the news-driven stock movement prediction. A recurrent state transition model is constructed, which better captures a gradual process of stock movement continuously by modeling the correlation between past and future price movements. By separating the effects of news and noise, a noisy random factor is also explicitly fitted based on the recurrent states. Results show that the proposed model outperforms strong baselines. Thanks to the use of attention over news events, our model is also more explainable. To our knowledge, we are the first to explicitly model both events and noise over a fundamental stock value state for news-driven stock movement prediction.