A Conceptual Model of Investment-Risk Prediction in the Stock Market Using Extreme Value Theory with Machine Learning: A Semisystematic Literature Review
Open Access
Abstract
The COVID-19 pandemic has been an extraordinary event, the type of event that rarely occurs but that has major impacts on the stock market. The pandemic has created high volatility and caused extreme fluctuations in the stock market. The stock market can be characterized as either linear or nonlinear. One method that can detect extreme fluctuations is extreme value theory (EVT). This study employed a semisystematic literature review on the use of the EVT method to estimate investment risk in the stock market. The literature used was selected by applying the preferred reporting items for systematic review and meta-analyses (PRISMA) guidelines, sourced from the ScienceDirect.com, ProQuest, and Scopus databases. A bibliometric analysis was conducted to determine the study characteristics and identify any research gaps. The results of the analysis show that studies on this topic are rarely carried out. Research in this field is generally performed only in univariate cases and is very complicated in multivariate cases. Given these limitations, further research could focus on developing a conceptual model that is dynamic and sensitive to extreme fluctuations, with multivariable inputs, in order to predict investment risk. The model developed here considered the variables that affect stock price fluctuations as the input data. The combination of VaR–EVT and machine-learning methods is effective in increasing model accuracy because it combines linear and nonlinear models.Keywords
Funding Information
- Universitas Padjadjaran (2203/UN6.3.1/PT.00/2022)
This publication has 45 references indexed in Scilit:
- Intraday portfolio risk management using VaR and CVaR:A CGARCH-EVT-Copula approachInternational Journal of Forecasting, 2019
- The Asymptotic Decision Scenarios of an Emerging Stock Exchange Market: Extreme Value Theory and Artificial Neural NetworkRisks, 2018
- A Performance Comparison of Neural Networks in Forecasting Stock Price TrendInternational Journal of Computational Intelligence Systems, 2017
- Predicting the Direction of Stock Market Index Movement Using an Optimized Artificial Neural Network ModelPLOS ONE, 2016
- Managing extreme risk in some major stock markets: An extreme value approachInternational Review of Economics & Finance, 2015
- Value-at-Risk models and Basel capital chargesJournal of Financial Stability, 2012
- From value at risk to stress testing: The extreme value approachJournal of Banking & Finance, 2000
- The Extreme Value Method for Estimating the Variance of the Rate of ReturnThe Journal of Business, 1980
- Statistical Inference Using Extreme Order StatisticsThe Annals of Statistics, 1975
- Residual Life Time at Great AgeThe Annals of Probability, 1974