Tensor Representation in High-Frequency Financial Data for Price Change Prediction

TL;DR

This paper demonstrates that tensor-based multilinear models significantly improve mid-price prediction accuracy in high-frequency trading by effectively capturing complex multichannel time-series data, outperforming traditional vector-based methods.

Contribution

It introduces the application of tensor representations and multilinear models to high-frequency financial data, showing their superiority over existing approaches in price change prediction.

Findings

Tensor models outperform vector-based approaches.

Multilinear methods achieve higher prediction accuracy.

Large-scale experiments validate the effectiveness of tensor representations.

Abstract

Nowadays, with the availability of massive amount of trade data collected, the dynamics of the financial markets pose both a challenge and an opportunity for high frequency traders. In order to take advantage of the rapid, subtle movement of assets in High Frequency Trading (HFT), an automatic algorithm to analyze and detect patterns of price change based on transaction records must be available. The multichannel, time-series representation of financial data naturally suggests tensor-based learning algorithms. In this work, we investigate the effectiveness of two multilinear methods for the mid-price prediction problem against other existing methods. The experiments in a large scale dataset which contains more than 4 millions limit orders show that by utilizing tensor representation, multilinear models outperform vector-based approaches and other competing ones.