An Analysis of the Performance and Interpretability of Machine Learning Classification Algorithms to Predict Long-Term Share Returns on the JSE

Aug 3, 2026

Upload by Skyler

The study addresses the complex task of predicting long-term share returns and improving investment-strategy decisions through machine learning. Although such models can enhance predictive accuracy, their lack of transparency and interpretability restricts real-world adoption. The research investigates machine learning classifiers for the Johannesburg Stock Exchange using fundamental data and evaluates interpretability of top performers. Eight algorithms are compared for 12-month tercile returns over two decades, with ensemble methods—XGBoost, Random Forest, and GradBoost—showing the strongest results.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages173

Reading Time7 h 16 min

AccessFree to download

Introduction

Research Aim and Objectives

Tools and Approach

Overall Approach

Dataset

Algorithms

Evaluation

Tools

Contributions

Structure of the Dissertation

Literature Review

The Share Market: Johannesburg Stock Exchange (JSE)

AN ANALYSIS OF THE PERFORMANCE AND INTERPRETABILITY OF MACHINE LEARNING CLASSIFICATION ALGORITHMS TO PREDICT LONG-TERM SHARE RETURNS ON THE JSE BY JAMIE BOAKES SUBMITTED IN PARTIAL FULFILMENT FOR THE REQUIREMENTS FOR THE DEGREE MSC INFORMATION TECHNOLOGY DEPARTMENT OF COMPUTER SCIENCE UNIVERSITY OF CAPE TOWN Supervised By: Associate Professor Deshendran Moodley May 2024 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 I the undersigned, Jamie Edward Russell Boakes, hereby declare that the work on which this dissertation 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. Abstract The prediction of long-term share returns is an essential yet complex task in financial analysis and formulating investment strategy. Machine learning is a promising approach for improving the accuracy of these predictions. However, the outputs of machine learning models are not transparent or interpretable, which limits their usability for real-world decision making. There is a lack of research on the use of machine learning algorithms to predict long-term share returns on the Johannesburg Stock Exchange (JSE), with no studies that specifically examine the interpretability of machine learning algorithms. This study investigates the use of machine learning algorithms to predict long-term share returns on the JSE based on fundamental data and analyses the interpretability of the top performing algorithms. Based on a review of the literature, eight machine learning classification algorithms were selected and compared to predict tercile class 12-month share returns using fundamental data, spanning a period of two decades. The XGBoost, Random Forest, and GradBoost algorithms were found to outperform the Support Vector Classifier, Logistic Regression, Decision Tree, Artificial Neural Network, and AdaBoost algorithms. XGBoost and Random Forest were further investigated using SHAP (SHapley Additive exPlanations) global summary plots to identify the most influential input features and to analyse the interpretability of these algorithms. The study found that ensemble-based classification algorithms, i.e. XGBoost, Random Forest and GradBoost, outperformed the other algorithms. Further analysis of the results varied, with some sectors outperforming the overall market. An analysis of the input features identified the most important valuation and profitability ratios that contributed to prediction performance, and thus improves the transparency and interpretability of the models. This research is the first to comprehensively compare and analyse the interpretability of machine learning algorithms to predict long-term share returns on the JSE. Contents Declaration...............................................................................................................................................................i Abstract .................................................................................................................................................................. ii List of Tables ...................................................................................................................................................... viii List of Figures ..................................................................................................................................................... viii Glossary of Terms ..............................................................................................

FAQs

Why is interpretability important in machine learning for financial decision-making?

Machine learning model outputs are often not transparent or interpretable, limiting usability for real-world investment decisions. Interpretable models improve transparency about which inputs drive predictions.

Which machine learning algorithms performed best for predicting long-term share returns on the JSE?

XGBoost, Random Forest, and GradBoost outperformed the other compared algorithms, including Support Vector Classifier, Logistic Regression, Decision Tree, Artificial Neural Network, and AdaBoost.

How did the study analyze interpretability of the top-performing models?

XGBoost and Random Forest were further analyzed using SHAP global summary plots to identify the most influential input features and assess model interpretability.

Aug 3, 2026

Upload by Skyler