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

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

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 excessiv...

Full description

Bibliographic Details
Main Authors: Yong Shi, Wei Dai, Wen Long
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-05-01
Series:Frontiers in Physics
Subjects:
hybrid model
deep learning
conditional duration
tick data
distribution forecasting
Online Access:https://www.frontiersin.org/articles/10.3389/fphy.2021.651528/full

Internet

https://www.frontiersin.org/articles/10.3389/fphy.2021.651528/full

Similar Items