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

Mostafa Shabani, Dat Thanh Tran, Martin Magris, Juho Kanniainen, Alexandros Iosifidis

    Publikation: Bidrag til bog/antologi/rapport/proceedingKonferencebidrag i proceedingsForskningpeer review

    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.

    OriginalsprogEngelsk
    Titel30th European Signal Processing Conference, EUSIPCO 2022 - Proceedings
    Antal sider5
    ForlagIEEE
    Publikationsdatookt. 2022
    Sider1487-1491
    ISBN (Trykt)978-1-6654-6799-5
    ISBN (Elektronisk)978-90-827970-9-1
    DOI
    StatusUdgivet - okt. 2022
    Begivenhed30th European Signal Processing Conference (EUSIPCO) - Belgrade, Serbien
    Varighed: 29 aug. 20222 sep. 2022

    Konference

    Konference30th European Signal Processing Conference (EUSIPCO)
    Land/OmrådeSerbien
    ByBelgrade
    Periode29/08/202202/09/2022

    Fingeraftryk

    Dyk ned i forskningsemnerne om 'Multi-head Temporal Attention-Augmented Bilinear Network for Financial time series prediction'. Sammen danner de et unikt fingeraftryk.

    Citationsformater