Forecasting equity returns remains challenging because financial markets exhibit nonlinear dynamics, volatility clustering, and complex temporal dependencies that are difficult to capture using a single modelling approach. Traditional statistical models can capture dependence and volatility dynamics, while deep learning models are capable of learning nonlinear temporal patterns. This study evaluates the forecasting performance of traditional statistical models (ARIMA and GARCH), deep learning models (TCN and GRU), and hybrid models (ARIMA-TCN, ARIMA-GRU, GARCH-TCN, and GARCH-GRU) for forecasting the FTSE/JSE Top 40 index in South Africa. Daily closing prices comprising 4159 observations from 2010 to 2026 were analysed, with model performance evaluated on log returns using MSE, RMSE, and MAE, with the Naïve model used as a benchmark. The results show that all competing models substantially outperformed the Naïve benchmark, while the TCN outperformed the standalone GRU. GARCH-based models also demonstrated strong forecasting performance, highlighting the relevance of volatility dynamics in forecasting equity returns. Although GARCH-GRU recorded the lowest MSE, RMSE, and MAE among the models evaluated, its performance was very similar to that of the GARCH (2,2) model. The Diebold-Mariano test further showed no statistically significant difference in predictive accuracy between GARCH-GRU and (DM = 0.9495; p = 0.3424). These findings indicate that GARCH-GRU and provide statistically comparable forecasting performance, suggesting that the additional complexity of the hybrid framework does not necessarily result in a significant improvement in predictive accuracy. This study contributes to the financial forecasting literature by providing empirical evidence from an emerging African equity market and demonstrating the importance of volatility modelling and complementary statistical–deep learning approaches for forecasting FTSE/JSE Top 40 log returns.
This study compares the predictive performance of traditional multivariate time series models and machine learning (ML) techniques in modelling perceived feelings of safety among South African residents. The analysis uses secondary data from the Governance, Public Safety, and Justice Survey conducted by Statistics South Africa, covering 2013/2014 to 2023/2024 and comprising 215,301 observations. Perceived safety while walking alone in the neighbourhood during the day and after dark served as the response variables, while socio-economic characteristics such as age, sex, province, and main source of income were included as predictors. A Vector Autoregressive Moving Average (VARMA) model was estimated alongside Random Forest (RF) and Light Gradient Boosting Machine (LightGBM) algorithms. VARMA (2,2) and VARMA (3,1) provided the best statistical fit for daytime and after-dark safety perceptions, respectively. However, ML models achieved higher predictive accuracy overall, with RF outperforming both LightGBM and VARMA in capturing nonlinear relationships and short-term dynamics. The findings underscore the value of integrating ML into public safety modelling to enhance evidence-based planning and socio-economic policy development in South Africa. Future research should consider integrating higher-frequency and alternative data sources, such as administrative crime statistics and real-time behavioural data to improve model sensitivity and forecasting accuracy.