Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression

作者：

Highlights：

• MSA outperforms more frequently than all other methods.

• GMDH is the most stable in terms of outperforming random walk (75% of cases).

• The results show better forecasting performance of longer period data.

• The market has been less efficient during Covid-19.

摘要

•MSA outperforms more frequently than all other methods.•GMDH is the most stable in terms of outperforming random walk (75% of cases).•The results show better forecasting performance of longer period data.•The market has been less efficient during Covid-19.

论文关键词：CDS spreads,SVM,GMDH,LSTM,Markov switching autoregression,Covid-19

论文评审过程：Received 26 February 2021, Revised 1 January 2022, Accepted 14 January 2022, Available online 22 January 2022, Version of Record 25 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116553