Low-Rank Temporal Attention-Augmented Bilinear Network for financial time-series forecasting

TL;DR

This paper introduces a low-rank tensor approximation of a temporal attention-augmented bilinear network to improve efficiency and speed in high-frequency financial time-series forecasting.

Contribution

It proposes a novel low-rank tensor version of an existing model, enhancing parameter efficiency and inference speed for financial data prediction.

Findings

Reduced model parameters significantly

Maintained high forecasting accuracy

Faster inference times

Abstract

Financial market analysis, especially the prediction of movements of stock prices, is a challenging problem. The nature of financial time-series data, being non-stationary and nonlinear, is the main cause of these challenges. Deep learning models have led to significant performance improvements in many problems coming from different domains, including prediction problems of financial time-series data. Although the prediction performance is the main goal of such models, dealing with ultra high-frequency data sets restrictions in terms of the number of model parameters and its inference speed. The Temporal Attention-Augmented Bilinear network was recently proposed as an efficient and high-performing model for Limit Order Book time-series forecasting. In this paper, we propose a low-rank tensor approximation of the model to further reduce the number of trainable parameters and increase its speed.