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

TY - GEN

T1 - Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction

AU - Shabani, Mostafa

AU - Tran, Dat Thanh

AU - Magris, Martin

AU - Kanniainen, Juho

AU - Iosifidis, Alexandros

PY - 2022/10

Y1 - 2022/10

N2 - 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.

AB - 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.

KW - Attention mechanism

KW - Deep learning

KW - Financial Time-series

KW - Limit Order Book

UR - http://www.scopus.com/inward/record.url?scp=85141011086&partnerID=8YFLogxK

U2 - 10.23919/EUSIPCO55093.2022.9909957

DO - 10.23919/EUSIPCO55093.2022.9909957

M3 - Article in proceedings

SN - 978-1-6654-6799-5

SP - 1487

EP - 1491

BT - 30th European Signal Processing Conference, EUSIPCO 2022 - Proceedings

PB - IEEE

T2 - 30th European Signal Processing Conference (EUSIPCO)

Y2 - 29 August 2022 through 2 September 2022

ER -