Pre-Finetuning with Impact Duration Awareness for Stock Movement Prediction
This work addresses a specific gap in financial forecasting for investors and researchers, but it is incremental as it builds on existing pre-finetuning methods with a new dataset.
The paper tackles the problem of predicting stock movements by addressing the overlooked aspect of news impact duration, introducing a new dataset (IDED) and showing that pre-finetuning language models with it improves performance in text-based predictions.
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.