Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction

TL;DR

This paper introduces a new dataset and method for improving stock movement prediction by estimating the impact duration of news events, emphasizing the importance of impact duration awareness in financial forecasting.

Contribution

The paper presents the Impact Duration Estimation Dataset (IDED) and demonstrates that pre-finetuning language models with it improves stock prediction accuracy.

Findings

Pre-finetuning with IDED enhances prediction performance.

Impact duration estimation outperforms sentiment analysis in this context.

Open-sourced dataset and models for academic research.

Abstract

Understanding the duration of news events' impact on the stock market is crucial for effective time-series forecasting, yet this facet is largely overlooked in current research. This paper addresses this research gap by introducing a novel dataset, the Impact Duration Estimation Dataset (IDED), specifically designed to estimate impact duration based on investor opinions. Our research establishes that pre-finetuning language models with IDED can enhance performance in text-based stock movement predictions. In addition, we juxtapose our proposed pre-finetuning task with sentiment analysis pre-finetuning, further affirming the significance of learning impact duration. Our findings highlight the promise of this novel research direction in stock movement prediction, offering a new avenue for financial forecasting. We also provide the IDED and pre-finetuned language models under the CC BY-NC-SA 4.0 license for academic use, fostering further exploration in this field.