Predicting Chinese bond market turbulences: Attention-BiLSTM based early warning system

Peiwan Wang, Lu Zong, Yurun Yang

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

1 Citation (Scopus)

Abstract

The study aims to construct an effective early warning system (EWS) to predict the crisis triggered turbulence in Chinese bond market by integrating the volatility regime switching model, SWARCH, to improve the crisis classifying precision, and the stylized predictive model, Attention-BiLSTM of attention mechanism based deep neural networks, to resolve the predicting hysteresis. The model versatility and comparability are investigated and testified by applying multiple prominent EWS models to bonds with different credit rating levels. The hybrid EWS also specifies the leading factors relating to the bond credit rating, that will practically instruct governors and market participants to focus on either the national economy associated or the corporate finance concerned factors according to the bond varying credit risks to make more effective predictions.

Original languageEnglish
Title of host publicationProceedings of the 2020 2nd International Conference on Big Data Engineering, BDE 2020
PublisherAssociation for Computing Machinery
Pages91-104
Number of pages14
ISBN (Electronic)9781450377225
DOIs
Publication statusPublished - 29 May 2020
Event2nd International Conference on Big Data Engineering, BDE 2020 - Shanghai, China
Duration: 29 May 202031 May 2020

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Big Data Engineering, BDE 2020
Country/TerritoryChina
CityShanghai
Period29/05/2031/05/20

Keywords

  • Attention mechanism
  • Deep neural networks
  • Early warning system
  • Regime switching ARCH
  • Volatility classified crisis

Fingerprint

Dive into the research topics of 'Predicting Chinese bond market turbulences: Attention-BiLSTM based early warning system'. Together they form a unique fingerprint.

Cite this