Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction

TL;DR

This paper introduces a multi-head temporal attention-augmented bilinear network designed for financial time series prediction, demonstrating improved accuracy in forecasting mid-price movements using large-scale market data.

Contribution

It proposes a novel neural layer combining temporal and multi-head attention to better capture important temporal features in financial data.

Findings

Multi-head attention improves prediction accuracy.

The model outperforms baseline methods.

Effective on large-scale limit-order book data.

Abstract

Financial time-series forecasting is one of the most challenging domains in the field of time-series analysis. This is mostly due to the highly non-stationary and noisy nature of financial time-series data. With progressive efforts of the community to design specialized neural networks incorporating prior domain knowledge, many financial analysis and forecasting problems have been successfully tackled. The temporal attention mechanism is a neural layer design that recently gained popularity due to its ability to focus on important temporal events. In this paper, we propose a neural layer based on the ideas of temporal attention and multi-head attention to extend the capability of the underlying neural network in focusing simultaneously on multiple temporal instances. The effectiveness of our approach is validated using large-scale limit-order book market data to forecast the direction of mid-price movements. Our experiments show that the use of multi-head temporal attention modules leads to enhanced prediction performances compared to baseline models.