A machine learning hybrid approach to forecasting equity returns volatility - A South African perspective

Aug 4, 2026

Upload by Sage

Scholars and market practitioners remain focused on improving forecasts of financial return volatility, where different modeling families show varying accuracy across conditions. This study extends machine learning research by developing hybrid volatility forecasting methods for South African equities, combining well-fitting ARCH-type econometric specifications with LSTM. Guided by volatility stylised-facts capture, it evaluates GARCH, EGARCH, and TGARCH bases alongside seven LSTM hybrids and a GARCH-EGARCH-TGARCH average model. Using JSE All Share Index daily data (2004–2022), results are compared via RMSE, MAE, MAPE and tested with the Wilcoxon signed-rank test.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages73

Reading Time3 h 4 min

AccessFree to download

1. Introduction

1.1. Background

1.2. The aim of the study

1.3. Study questions

A machine learning hybrid approach to forecasting equity returns volatility: A South African perspective. by Student: Mr Tabataba Simon Tloubatla Student number: TLBTAB001 SUBMITTED TO THE UNIVERSITY OF CAPE TOWN In partial fulfilment of the requirements for the degree: M. Com in Finance specialising in Corporate Finance and Valuations Faculty of Finance and Tax UNIVERSITY OF CAPE TOWN Date of submission: 11 February 2024 Supervisor: Prof Francois Toerien Faculty of Commerce, Department of Finance and Tax, University of Cape Town The copyright of this thesis vests in the author. No quotation from it or information derived from it is to be published without full acknowledgement of the source. The thesis is to be used for private study or noncommercial research purposes only. Published by the University of Cape Town (UCT) in terms of the non-exclusive license granted to UCT by the author. Declaration page You must include a signed and dated declaration in the front of your dissertation/thesis. Please use the standard format shown below: DECLARATION I, Mr TS Tloubatla, hereby declare that the work on which this dissertation/thesis is based is my original work (except where acknowledgements indicate otherwise) and that neither the whole work nor any part ofit has been, is being, or is to be submitted for another degree in this or any other university. I empower the university to reproduce for the purpose of study either the whole or any portion of the contents in any manner whatsoever. Signature: 12/02/2024 Date: A machine learning hybrid approach to forecasting equity return volatility: a South African perspective. Abstract For many years, scholars and professionals in the financial markets have been deeply interested in the forecasting of financial market return volatility. There are many methods for predicting the volatility of financial market returns, and various studies have indicated differing degrees of accuracy in this regard. Research on describing the effectiveness of various approaches under various conditions is still ongoing. This field has moved from simple econometric methodologies like Moving Averages (MA), ARCH-type models and stochastic volatility, to more complex models like LSTM (Long-Short-Term-memory) and SVM (Support Vector Machines)(specifically machine learning algorithms). Machine learning in various forms is currently being explored as an alternative for forecasting the volatility of financial market returns. In this study this exploration is continued by considering a hybrid-based methodology to forecast this volatility, specifically in the South African equities market. There are two guiding principles for this study. The first principle is that specific ARCH-type models that achieve a superior fit to the dataset in question (the JSE All Share Index in this study) can be used in combination with machine learning (ML) models to forecast the volatility in financial market returns. The second principle stems from the work of earlier authors who have demonstrated the suitability and use of LSTM as a ML model that is effective in generating hybrid volatility forecasting models in conjunction with other ARCH-type models. The first guidance is based on the view that accuracy in volatility prediction depends on the ability of a model or group of models to capture volatility stylised facts inherent in a time series dataset used. The approach is based on the idea that various econometric and machine learning forecasting models each have their own advantages and disadvantages, and that combining them results in a stronger forecasting approach. The search for ARCH-type models showing a superior data fit for the Johannesburg Stock Exchange All Share Index (JSE ALSI) revealed the following models as suitable: GARCH(G), EGARCH(E) and TGARCH(T) . The study then applies the base econometric models to LSTM and produces seven hybrid models, namely G-LSTM, E-LSTM, T-L

FAQs

What is the core objective of the study?

To forecast equity return volatility in the South African equities market using hybrid methods that combine ARCH-type econometric models with machine learning (LSTM).

Which model families and hybrid combinations are used?

The econometric bases are GARCH(G), EGARCH(E), and TGARCH(T), which are combined with LSTM to form seven hybrids (G-LSTM, E-LSTM, T-LSTM, GE-LSTM, GT-LSTM, ET-LSTM, and GET-LSTM) plus a simple averaged model.

How is model performance evaluated and significance tested?

Out-of-sample performance is measured using RMSE, MAE, and MAPE, and forecast significance is assessed with the Wilcoxon signed-rank test.

Aug 4, 2026

Upload by Sage