A New Deep Learning-Based Zero-Inflated Duration Model for Financial Data Irregularly Spaced in Time

Frontiers in Physics

Wen Long¹  Wei Dai¹  Yong Shi² 

[1] School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China;Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China;Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing, China;School of Economics and Management, University of Chinese Academy of Sciences, Beijing, China;Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences, Beijing, China;Research Center on Fictitious Economy and Data Science, Chinese Academy of Sciences, Beijing, China;College of Information Science and Technology, University of Nebraska at Omaha, Omaha, NE, United States;

关键词: hybrid model;    deep learning;    conditional duration;    tick data;    distribution forecasting;   

DOI  :  10.3389/fphy.2021.651528

来源: Frontiers

【 摘 要 】

In stock trading markets, trade duration (i. e., inter-arrival times of trades) usually exhibits high uncertainty and excessive zero values. To forecast conditional distribution of trade duration, this study proposes a hybrid model called “DL-ZIACD” for short, which addresses the problem of excessive zero values by a zero-inflated distribution. Meanwhile, dynamics of the distribution time-varying parameters are captured by a specially designed deep learning (DL) architecture in which the behavioral patterns of large traders and small individual traders are represented separately by different blocks. The proposed hybrid model takes advantage of the strong fitting ability of deep learning methods while allowing for providing a probabilistic output. This paper empirically applied the established model to a large-scale dataset, containing 9,900,000 transactions of the Chinese Shenzhen Stock Exchange 100 Index (SZSE 100) constituents. To the best of our knowledge, no previous studies have applied conditional duration models to a dataset of such a large scale. For both the central location forecasting and the extreme quantile forecasting, our proposed model exhibited significant superiority over the benchmark models, which indicates that our DL-ZIACD model can provide accurate forecasts in conditional duration distribution.

【 授权许可】

CC BY