Standard

Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression. / Vukovic, Darko B. ; Romanyuk, Kirill ; Ivashchenko, Sergey ; Grigorieva, Elena M. .

In: Expert Systems with Applications, Vol. 194, No. 3, 116553, 2022.

Research output: Contribution to journal › Article › peer-review

Harvard

Vukovic, DB, Romanyuk, K, Ivashchenko, S & Grigorieva, EM 2022, 'Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression', Expert Systems with Applications, vol. 194, no. 3, 116553. https://doi.org/10.1016/j.eswa.2022.116553

APA

Vukovic, D. B., Romanyuk, K., Ivashchenko, S., & Grigorieva, E. M. (2022). Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression. Expert Systems with Applications, 194(3), [116553]. https://doi.org/10.1016/j.eswa.2022.116553

Vancouver

Vukovic DB, Romanyuk K, Ivashchenko S, Grigorieva EM. Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression. Expert Systems with Applications. 2022;194(3). 116553. https://doi.org/10.1016/j.eswa.2022.116553

Author

Vukovic, Darko B. ; Romanyuk, Kirill ; Ivashchenko, Sergey ; Grigorieva, Elena M. . / Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression. In: Expert Systems with Applications. 2022 ; Vol. 194, No. 3.

BibTeX

@article{2934def9756c4eb09e84777b2d50b3e9,
title = "Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression",
abstract = "This paper investigates the forecasting performance for credit default swap (CDS) spreads by Support Vector Machines (SVM), Group Method of Data Handling (GMDH), Long Short-Term Memory (LSTM) and Markov switching autoregression (MSA) for daily CDS spreads of the 513 leading US companies, in the period 2009–2020. The goal of this study is to test the forecasting performance of these methods before and during the Covid-19 pandemic and to check whether there are changes in the market efficiency. MSA outperforms all other methods most frequently. GMDH breaks the efficient market hypothesis more frequently (75%) than other methods. The change of the relative predictability during Covid-19 is small with some increase of the advantage of the investigated methods over a benchmark. We find that the market has been less efficient during Covid-19, however, there are no huge differences in prediction performances before and during the Covid-19 period..",
keywords = "CDS spreads, SVM, GMDH, LSTM, Markov switching autoregression, Covid-19",
author = "Vukovic, {Darko B.} and Kirill Romanyuk and Sergey Ivashchenko and Grigorieva, {Elena M.}",
note = "Vukovic, D. Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression / D. Vukovic, K. Romanyuk, E. M. Grigorieva // Expert Systems with Applications. - 2022.",
year = "2022",
doi = "10.1016/j.eswa.2022.116553",
language = "English",
volume = "194",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier",
number = "3",

}

RIS

TY - JOUR

T1 - Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression

AU - Vukovic, Darko B.

AU - Romanyuk, Kirill

AU - Ivashchenko, Sergey

AU - Grigorieva, Elena M.

N1 - Vukovic, D. Are CDS spreads predictable during the Covid-19 pandemic? Forecasting based on SVM, GMDH, LSTM and Markov switching autoregression / D. Vukovic, K. Romanyuk, E. M. Grigorieva // Expert Systems with Applications. - 2022.

PY - 2022

Y1 - 2022

N2 - This paper investigates the forecasting performance for credit default swap (CDS) spreads by Support Vector Machines (SVM), Group Method of Data Handling (GMDH), Long Short-Term Memory (LSTM) and Markov switching autoregression (MSA) for daily CDS spreads of the 513 leading US companies, in the period 2009–2020. The goal of this study is to test the forecasting performance of these methods before and during the Covid-19 pandemic and to check whether there are changes in the market efficiency. MSA outperforms all other methods most frequently. GMDH breaks the efficient market hypothesis more frequently (75%) than other methods. The change of the relative predictability during Covid-19 is small with some increase of the advantage of the investigated methods over a benchmark. We find that the market has been less efficient during Covid-19, however, there are no huge differences in prediction performances before and during the Covid-19 period..

AB - This paper investigates the forecasting performance for credit default swap (CDS) spreads by Support Vector Machines (SVM), Group Method of Data Handling (GMDH), Long Short-Term Memory (LSTM) and Markov switching autoregression (MSA) for daily CDS spreads of the 513 leading US companies, in the period 2009–2020. The goal of this study is to test the forecasting performance of these methods before and during the Covid-19 pandemic and to check whether there are changes in the market efficiency. MSA outperforms all other methods most frequently. GMDH breaks the efficient market hypothesis more frequently (75%) than other methods. The change of the relative predictability during Covid-19 is small with some increase of the advantage of the investigated methods over a benchmark. We find that the market has been less efficient during Covid-19, however, there are no huge differences in prediction performances before and during the Covid-19 period..

KW - CDS spreads

KW - SVM

KW - GMDH

KW - LSTM

KW - Markov switching autoregression

KW - Covid-19

U2 - 10.1016/j.eswa.2022.116553

DO - 10.1016/j.eswa.2022.116553

M3 - Article

VL - 194

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 3

M1 - 116553

ER -

ID: 101791811