LMLeonard Marevhula

Leonard Marevhula

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Leonard Marevhula has a total of 1 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Forecasting the South African Unemployment Rate: A Comparative Analysis of ARIMAX and LSTM Models

    by Israel Maingo, Leonard Marevhula

    This study looks into the predictive performance of linear econometric and deep learning methodologies for the South African unemployment rate quarterly data. In this paper, the Autoregressive Integrated Moving Average with exogenous variables (ARIMAX) model was compared to the Long Short-Term Memory (LSTM) network using unemployment rate quarterly data. Exploratory Data Analysis (EDA) suggested that the unemployment rate series is non-stationary, with structural breaks around 2020 and time-varying volatility. Stationarity tests established the need for differencing, whereas diagnostic tests revealed the presence of autocorrelation and ARCH effects in the raw data. The ARIMAX model added labour market covariates, and the differenced Not Economically Active (NEA) variable was statistically significant, whereas Discouraged workers were not. Although the ARIMAX model provided a good in-sample fit, residual diagnostics showed deviations from normality. Out-of-sample forecast study revealed moderate predictive accuracy, with relatively substantial forecast errors and increasing prediction intervals over time. In contrast, the LSTM model showed significant learning capacity, with early convergence and well-behaved residuals that meet both independence and homoskedasticity criteria. The model achieved significantly lower forecast errors, with RMSE, MAE, and MAPE values much lower than those of the ARIMAX model. Comparative forecast analysis using Diebold-Mariano (DM) test and model confidence Set (MCS) method and bootstrap confidence intervals consistently demonstrated the statistical superiority of the LSTM model. The findings give strong evidence that the LSTM model outperformed the ARIMAX model for projecting South African unemployment rate. The findings emphasise the importance of nonlinear modelling approaches in capturing complex labour market dynamics while also demonstrating the limitations of classic linear models. These findings also emphasise the importance of using nonlinear machine learning algorithms in macroeconomic forecasting.

  • Open Access

    CPI Inflation Rate: A Comparative Analysis of Traditional Basic Structural Model (BSM) and Artificial Neural Networks (ANN) Model for Accurate Predictions in South Africa

    by Israel Maingo, Leonard Marevhula

    Precise inflation prediction is crucial for the formulation of monetary policies and economic planning, especially in the case of developing countries like South Africa. This research investigates the predictive capabilities of conventional and machine learning models for forecasting the South African Consumer Price Index (CPI) inflation rate. The monthly values of the CPI inflation rate from January 2008 to October 2025, collected from Statistics South Africa, were considered. The models used were the Basic Structural Model (BSM), the Artificial Neural Network (ANN), and the combined hybrid BSM and ANN approach. The BSM model examines structural variables like trend and seasonality, and the model ANNs focus on nonlinearities. The model performance was assessed using the criteria of RMSE, MAE, and MASE performance measures, in the in-sample forecasting. The empirical analysis shows that the performance of the model ANN outperformed that of the BSM and hybrid BSM–ANN models considerably when compared using the in-sample forecasting, and its results were well-behaved without any features of autocorrelation and heteroscedasticity. The results showed that the combined hybrid BSM–ANN model was superior to the BSM and ANN models, although it may not necessarily outperform the other two, as the out-of-sample forecasts were more stable and reasonable.