Data normalization for bilinear structures in high-frequency financial time-series

Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

Abstrakti

Financial time-series analysis and forecasting have been extensively studied over the past decades, yet still remain as a very challenging research topic. Since the financial market is inherently noisy and stochastic, a majority of financial time-series of interests are non-stationary, and often obtained from different modalities. This property presents great challenges and can significantly affect the performance of the subsequent analysis/forecasting steps. Recently, the Temporal Attention augmented Bilinear Layer (TABL) has shown great performances in tackling financial forecasting problems. In this paper, by taking into account the nature of bilinear projections in TABL networks, we propose Bilinear Normalization (BiN), a simple, yet efficient normalization layer to be incorporated into TABL networks to tackle potential problems posed by non-stationarity and multimodalities in the input series. Our experiments using a large scale Limit Order Book (LOB) consisting of more than 4 million order events show that BiN-TABL outperforms TABL networks using other state-of-the-arts normalization schemes by a large margin.

AlkuperäiskieliEnglanti
OtsikkoProceedings of ICPR 2020 - 25th International Conference on Pattern Recognition
KustantajaIEEE
Sivut7287-7292
Sivumäärä6
ISBN (elektroninen)978-1-7281-8808-9
DOI - pysyväislinkit
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
Tapahtuma25th International Conference on Pattern Recognition, ICPR 2020 - Virtual, Milan, Italia
Kesto: 10 tammik. 202115 tammik. 2021

Julkaisusarja

NimiProceedings - International Conference on Pattern Recognition
ISSN (painettu)1051-4651

Conference

Conference25th International Conference on Pattern Recognition, ICPR 2020
Maa/AlueItalia
KaupunkiVirtual, Milan
Ajanjakso10/01/2115/01/21

Julkaisufoorumi-taso

  • Jufo-taso 1

!!ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Sormenjälki

Sukella tutkimusaiheisiin 'Data normalization for bilinear structures in high-frequency financial time-series'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä