ESG volatility prediction using GARCH and LSTM models

Akshay Kumar Mishra, Rahul Kumar, Debi Prasad Bal

This study aims to predict the ESG (environmental, social, and governance) return volatility based on ESG index data from 26 October 2017 and 31 March 2023 in the case of India. In this study, we utilized GARCH (Generalized Autoregressive Conditional Heteroskedasticity) and LSTM (Long Short-Term Memory) models for forecasting the return of ESG volatility and to evaluate the model's suitability for prediction. The study\'s findings demonstrate the GARCH effect inside the ESG return volatility data, indicating the occurrence of volatility in response to market fluctuations. This study provides insight concerning the suitability of models for volatility predictions. Moreover, based on the analysis of the return volatility of the ESG index, the GARCH model is more appropriate than the LSTM model.

MoreLess

Year of publication:	2023
Authors:	Mishra, Akshay Kumar ; Kumar, Rahul ; Bal, Debi Prasad
Published in:	Financial internet quarterly. - Rzeszów : University of Information Technology and Management, ISSN 2719-3454, ZDB-ID 3121236-0. - Vol. 19.2023, 4, p. 97-114
Subject:	ESG Volatility \| GARCH \| LSTM model \| Volatilität \| Volatility \| ARCH-Modell \| ARCH model \| Prognoseverfahren \| Forecasting model \| Corporate Social Responsibility \| Corporate social responsibility \| Theorie \| Theory \| Nachhaltige Kapitalanlage \| Sustainable investment \| Börsenkurs \| Share price \| Zeitreihenanalyse \| Time series analysis