$\text{COVID19-HPSMP}$: COVID-19 adopted Hybrid and Parallel deep information fusion framework for stock price movement prediction

Highlights

• Introduction of COVID-19 related PRIce MOvement prediction (COVID19 PRIMO) dataset.

• Proposing COVID-19 adopted hybrid deep fusion framework for stock price prediction.

• Integration of COVID-19 related Twitter data with extended horizon market data.

• Generalization performance of price movement prediction across various scenarios.

• Outperforming stand-alone (non-hybrid) deep learning-based price prediction models.

Abstract

The novel of coronavirus (COVID-19) has suddenly and abruptly changed the world as we knew at the start of the 3rd decade of the 21st century. Particularly, COVID-19 pandemic has negatively affected financial econometrics and stock markets across the globe. Artificial Intelligence (AI) and Machine Learning (ML)-based prediction models, especially Deep Neural Network (DNN) architectures, have the potential to act as a key enabling factor to reduce the adverse effects of the COVID-19 pandemic and future possible ones on financial markets. In this regard, first, a unique COVID-19 related PRIce MOvement prediction ($\text{COVID19 PRIMO}$) dataset is introduced in this paper, which incorporates effects of social media trends related to COVID-19 on stock market price movements. Afterwards, a novel hybrid and parallel DNN-based framework is proposed that integrates different and diversified learning architectures. Referred to as the COVID-19 adopted Hybrid and Parallel deep fusion framework for Stock price Movement Prediction ($\text{COVID19-HPSMP}$), innovative fusion strategies are used to combine scattered social media news related to COVID-19 with historical mark data. The proposed $\text{COVID19-HPSMP}$ consists of two parallel paths (hence hybrid), one based on Convolutional Neural Network (CNN) with Local/Global Attention modules, and one integrated CNN and Bi-directional Long Short term Memory (BLSTM) path. The two parallel paths are followed by a multilayer fusion layer acting as a fusion center that combines localized features. Performance evaluations are performed based on the introduced $\text{COVID19 PRIMO}$ dataset illustrating superior performance of the proposed framework.