A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic

Ray R. Hashemi; Omid M. Ardakani; Daniel Bekker; James D. Griffith

doi:10.1109/CSCI62032.2023.00107

A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic

Ray R. Hashemi, Omid M. Ardakani, Daniel Bekker, James D. Griffith

Georgia Southern University

Research output: Contribution to book or proceeding › Conference article › peer-review

Abstract

We analyze, design, implement, and validate a stochastic model for the economic recession using the financial outcomes of yield spread, crude oil prices, and stock market indices (volatility index and Wilshire 5000 total market index). The proposed model uses Markov Chain Model (MCM) and Hidden Markov Chain Model (HMCM) to (a) identify the impact of the COVID-19 pandemic on the recession by modeling the recession for two eras of 'Before' and 'During' the pandemic, (b) implement the 'trend' analysis by forecasting the value of the financial outcomes for a date in the future and predicts the recession for that date using the forecasted values, and (c) entertain 'what-if' scenarios about the recession status for sudden drastic increases in the financial outcomes, one at a time. Results reveal that for case (a) the pandemic's onset disrupted the predictability of financial indices, for case (b) the correct future prediction of indices and the recession probability index for the 'Before' dataset has a much higher margin over the 'During' dataset, and for case (c) the yield spread has the highest total percentage of drastic and moderate changes among prediction of its values and prediction of the recession.

Original language	English
Title of host publication	Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	605-610
Number of pages	6
ISBN (Electronic)	9798350361513
DOIs	https://doi.org/10.1109/CSCI62032.2023.00107
State	Published - 2023
Event	2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023 - Las Vegas, United States Duration: Dec 13 2023 → Dec 15 2023

Publication series

Name	Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023

Conference

Conference	2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023
Country/Territory	United States
City	Las Vegas
Period	12/13/23 → 12/15/23

Scopus Subject Areas

Artificial Intelligence
Computer Science Applications
Computational Mathematics

Keywords

COVID-19 Impact on macroeconomic and financial indicators
Markov Modeling
Stochastic modeling
Trend Analysis
What -if Analysls

Access to Document

10.1109/CSCI62032.2023.00107

https://ieeexplore.ieee.org/document/10590426

Cite this

Hashemi, R. R., Ardakani, O. M., Bekker, D., & Griffith, J. D. (2023). A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic. In Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023 (pp. 605-610). (Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCI62032.2023.00107

Hashemi, Ray R. ; Ardakani, Omid M. ; Bekker, Daniel et al. / A Markov-Based Economic Recession Modeling Through Financial Outcomes : Before and During the COVID-19 Pandemic. Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. pp. 605-610 (Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023).

@inproceedings{71629a3221e9433bab47d2a5be213a0b,

title = "A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic",

abstract = "We analyze, design, implement, and validate a stochastic model for the economic recession using the financial outcomes of yield spread, crude oil prices, and stock market indices (volatility index and Wilshire 5000 total market index). The proposed model uses Markov Chain Model (MCM) and Hidden Markov Chain Model (HMCM) to (a) identify the impact of the COVID-19 pandemic on the recession by modeling the recession for two eras of 'Before' and 'During' the pandemic, (b) implement the 'trend' analysis by forecasting the value of the financial outcomes for a date in the future and predicts the recession for that date using the forecasted values, and (c) entertain 'what-if' scenarios about the recession status for sudden drastic increases in the financial outcomes, one at a time. Results reveal that for case (a) the pandemic's onset disrupted the predictability of financial indices, for case (b) the correct future prediction of indices and the recession probability index for the 'Before' dataset has a much higher margin over the 'During' dataset, and for case (c) the yield spread has the highest total percentage of drastic and moderate changes among prediction of its values and prediction of the recession.",

keywords = "COVID-19 Impact on macroeconomic and financial indicators, Markov Modeling, Stochastic modeling, Trend Analysis, What -if Analysls",

author = "Hashemi, {Ray R.} and Ardakani, {Omid M.} and Daniel Bekker and Griffith, {James D.}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023 ; Conference date: 13-12-2023 Through 15-12-2023",

year = "2023",

doi = "10.1109/CSCI62032.2023.00107",

language = "English",

series = "Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "605--610",

booktitle = "Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023",

address = "United States",

}

Hashemi, RR , Ardakani, OM, Bekker, D & Griffith, JD 2023, A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic. in Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023. Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023, Institute of Electrical and Electronics Engineers Inc., pp. 605-610, 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023, Las Vegas, United States, 12/13/23. https://doi.org/10.1109/CSCI62032.2023.00107

A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic. / Hashemi, Ray R.; Ardakani, Omid M.; Bekker, Daniel et al.
Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023. Institute of Electrical and Electronics Engineers Inc., 2023. p. 605-610 (Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023).

Research output: Contribution to book or proceeding › Conference article › peer-review

TY - GEN

T1 - A Markov-Based Economic Recession Modeling Through Financial Outcomes

T2 - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023

AU - Hashemi, Ray R.

AU - Ardakani, Omid M.

AU - Bekker, Daniel

AU - Griffith, James D.

PY - 2023

Y1 - 2023

N2 - We analyze, design, implement, and validate a stochastic model for the economic recession using the financial outcomes of yield spread, crude oil prices, and stock market indices (volatility index and Wilshire 5000 total market index). The proposed model uses Markov Chain Model (MCM) and Hidden Markov Chain Model (HMCM) to (a) identify the impact of the COVID-19 pandemic on the recession by modeling the recession for two eras of 'Before' and 'During' the pandemic, (b) implement the 'trend' analysis by forecasting the value of the financial outcomes for a date in the future and predicts the recession for that date using the forecasted values, and (c) entertain 'what-if' scenarios about the recession status for sudden drastic increases in the financial outcomes, one at a time. Results reveal that for case (a) the pandemic's onset disrupted the predictability of financial indices, for case (b) the correct future prediction of indices and the recession probability index for the 'Before' dataset has a much higher margin over the 'During' dataset, and for case (c) the yield spread has the highest total percentage of drastic and moderate changes among prediction of its values and prediction of the recession.

AB - We analyze, design, implement, and validate a stochastic model for the economic recession using the financial outcomes of yield spread, crude oil prices, and stock market indices (volatility index and Wilshire 5000 total market index). The proposed model uses Markov Chain Model (MCM) and Hidden Markov Chain Model (HMCM) to (a) identify the impact of the COVID-19 pandemic on the recession by modeling the recession for two eras of 'Before' and 'During' the pandemic, (b) implement the 'trend' analysis by forecasting the value of the financial outcomes for a date in the future and predicts the recession for that date using the forecasted values, and (c) entertain 'what-if' scenarios about the recession status for sudden drastic increases in the financial outcomes, one at a time. Results reveal that for case (a) the pandemic's onset disrupted the predictability of financial indices, for case (b) the correct future prediction of indices and the recession probability index for the 'Before' dataset has a much higher margin over the 'During' dataset, and for case (c) the yield spread has the highest total percentage of drastic and moderate changes among prediction of its values and prediction of the recession.

KW - COVID-19 Impact on macroeconomic and financial indicators

KW - Markov Modeling

KW - Stochastic modeling

KW - Trend Analysis

KW - What -if Analysls

UR - http://www.scopus.com/inward/record.url?scp=85199997452&partnerID=8YFLogxK

U2 - 10.1109/CSCI62032.2023.00107

DO - 10.1109/CSCI62032.2023.00107

M3 - Conference article

AN - SCOPUS:85199997452

T3 - Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023

SP - 605

EP - 610

BT - Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 13 December 2023 through 15 December 2023

ER -

Hashemi RR , Ardakani OM, Bekker D, Griffith JD. A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic. In Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023. Institute of Electrical and Electronics Engineers Inc. 2023. p. 605-610. (Proceedings - 2023 International Conference on Computational Science and Computational Intelligence, CSCI 2023). doi: 10.1109/CSCI62032.2023.00107

A Markov-Based Economic Recession Modeling Through Financial Outcomes: Before and During the COVID-19 Pandemic

Abstract

Publication series

Conference

Scopus Subject Areas

Keywords

Access to Document

Other files and links

Fingerprint

Cite this