Stock Volatility Prediction Based on Transformer Model Using Mixed-Frequency Data

TL;DR

This paper proposes a transformer-based model that integrates mixed-frequency macroeconomic, technical, and search data to improve stock volatility prediction, demonstrating significant error reduction over baseline models.

Contribution

It introduces a novel approach combining macroeconomic, technical, and search data within a transformer framework using GARCH-MIDAS for data alignment, enhancing prediction accuracy.

Findings

Mean square error reduced from 1.00 to 0.86

Transformer model outperforms baseline models

Integration of subjective and objective factors improves accuracy

Abstract

With the increasing volume of high-frequency data in the information age, both challenges and opportunities arise in the prediction of stock volatility. On one hand, the outcome of prediction using tradition method combining stock technical and macroeconomic indicators still leaves room for improvement; on the other hand, macroeconomic indicators and peoples' search record on those search engines affecting their interested topics will intuitively have an impact on the stock volatility. For the convenience of assessment of the influence of these indicators, macroeconomic indicators and stock technical indicators are then grouped into objective factors, while Baidu search indices implying people's interested topics are defined as subjective factors. To align different frequency data, we introduce GARCH-MIDAS model. After mixing all the above data, we then feed them into Transformer model as part of the training data. Our experiments show that this model outperforms the baselines in terms of mean square error. The adaption of both types of data under Transformer model significantly reduces the mean square error from 1.00 to 0.86.