Data Normalization For Bilinear Structures In High-Frequency Financial Time-Series
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2020)
摘要
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.
更多查看译文
关键词
financial time-series analysis,financial market,financial forecasting problems,bilinear projections,bilinear normalization,data normalization,bilinear structures,high-frequency financial time-series,BiN-TABL,temporal attention augmented bilinear layer,limit order book,stochastic process
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络