The current study aims to model the South African crude oil prices using the hybrid of Box-Jenkins autoregressive integrated moving average (ARIMA) and Neural Networks (NNs). This study introduces a hybrid approach to forecasting methods aimed at resolving the issues of lack of precision in forecasting. The proposed methodology includes two models, namely, hybridisation of ARIMA with artificial neural network (ANN)-based Extreme Learning Machine (ELM) and ARIMA with general regression neural network (GRNN) to model both linear and nonlinear simultaneously. The models were compared with the base ARIMA model. The study utilised monthly time series data spanning from January 2021 to March 2023. The formal stationarity test confirmed that the crude oil price series is integrated of order one, I(1). For the linear process, the ARIMA (2,1,2) model was identified as the best fit for the series and successfully passed all diagnostic tests. The ARIMA-ANN-based ELM hybrid model outperformed both the individual ARIMA model and the ARIMA-GRNN hybrid. However, the ARIMA model also showed better performance than the ARIMA-GRNN hybrid, highlighting its strong competitiveness compared to the ARIMA-ANN-based ELM model. The hybrid models are recommended for use by policy makers and practitioners in general.
This study investigated the forecasting performance of the South African gold sales series using the seasonal autoregressive integrated moving average (SARIMA), generalised autoregressive conditionally heteroscedastic (GARCH), general regression neural network (GRNN) and artificial neural network (ANN)-based extreme learning machine (ELM). This study employed traditional methods and a recently developed ML method for single hidden-layer feed-forward neural networks (SLFNs). The findings revealed that was considered the best model for the gold sales series. The empirical findings demonstrated that the SARIMA model outperforms neural network-based models, providing the South African government and its lenders with a more reliable and cost-effective tool for predicting foreign exchange earnings from gold. This study contributes to the literature by providing one of the first comparative evaluations of traditional time-series models and advanced neural network methods for forecasting South African gold sales. This study is novel as it is a first-of-its-kind comparative application of traditional SARIMA and GARCH models alongside GRNN and ANN-based ELM methods to South African gold sales, revealing the superior forecasting performance of a traditional SARIMA model over advanced ML approaches. Future research should explore the development and application of hybrid models that integrate the strengths of linear SARIMA frameworks with the pattern-recognition capabilities of nonlinear ANN-based ELM models.
This study aimed to compare RNN algorithms and select the best-performing one between the GRU and LSTM for forecasting South African adjusted closing gold prices. The study used weekly secondary data sourced from Yahoo Finance and partitioned into three regimes, pre-COVID-19, COVID-19, and post-COVID-19, as well as the overall sample. The results indicated that the GRU algorithm consistently outperformed the LSTM algorithm across all evaluation periods based on the selected metrics, except during the COVID-19 period, where LSTM exhibited slightly better performance. Consequently, the GRU algorithm was identified as the best-performing algorithm for the South African adjusted closing gold price series. The relative effectiveness of GRU and LSTM algorithms in financial time series forecasting was clarified by the results. By integrating GRU-based forecasts into development finance frameworks, stakeholders can strengthen resilience against global shocks, improve financial planning, and foster more stable pathways for economic development. The authors recommended that future studies explore the performance of the GRU and LSTM with other advanced algorithms like Transformer architectures, hybrid algorithms, or traditional statistical methods to further enhance the forecasting robustness.
Background One of the disadvantages of the multilayer perception (MLP), which is a machine learning (ML) algorithm used in various fields, includes the uncontrollable growth of the number of total parameters, which may make MLP redundant in such high dimensions, and the uncontrollable growing stack of layers that ignores spatial information. Optimization algorithms were developed to determine the optimum number of parameters for MLP. Methods In this paper, the performances of the Genetic Algorithm (GA), Grasshopper Optimization Algorithm (GOA), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are compared. The study also sought to determine the impact of sample size variations on these optimization algorithms. A dataset on the direct marketing campaigns of a Portuguese banking institution from the UCI Machine Learning Repository with a sample size of 4 521 was used. Synthetic Minority Oversampling Technique (SMOTE) was applied to balance the binary dependent variables for the training data across various sample sizes. Results Based on the classification accuracy, specificity, sensitivity, precision, F-score, and execution time, the MLP based on CMA-ES (CMA-ES-MLP) was identified as the best classifier overall, as it maintained high rates of these classification metrics and was the second fastest to train. CMA-ES-MLP with a training sample of 5 114 was our ideal classifier, and it competes well with the classifiers that have been built by previous studies that used the same dataset. Conclusions The study found no consistent increase or decrease in the classification performance of the algorithms as the sample size increased, and the metrics fluctuated rapidly across sample sizes. It is recommended that future studies be conducted to compare the best-performing classifiers identified in previous studies with the CMA-ES-MLP in this study under the same experimental conditions.
Background One of the disadvantages of the multilayer perception (MLP), which is a machine learning (ML) algorithm used in various fields, includes the uncontrollable growth of the number of total parameters, which may make MLP redundant in such high dimensions, and the uncontrollable growing stack of layers that ignores spatial information. Optimization algorithms were developed to determine the optimum number of parameters for MLP. Methods In this paper, the performances of the Genetic Algorithm (GA), Grasshopper Optimization Algorithm (GOA), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are compared. The study also sought to determine the impact of sample size variations on these optimization algorithms. A dataset on the direct marketing campaigns of a Portuguese banking institution from the UCI Machine Learning Repository with a sample size of 4 521 was used. Synthetic Minority Oversampling Technique (SMOTE) was applied to balance the binary dependent variables for the training data across various sample sizes. Results Based on the classification accuracy, specificity, sensitivity, precision, F-score, and execution time, the MLP based on CMA-ES (CMA-ES-MLP) was identified as the best classifier overall, as it maintained high rates of these classification metrics and was the second fastest to train. CMA-ES-MLP with a training sample of 5 114 was our ideal classifier, and it competes well with the classifiers that have been built by previous studies that used the same dataset. Conclusions The study found no consistent increase or decrease in the classification performance of the algorithms as the sample size increased, and the metrics fluctuated rapidly across sample sizes. It is recommended that future studies be conducted to compare the best-performing classifiers identified in previous studies with the CMA-ES-MLP in this study under the same experimental conditions.
Background One of the disadvantages of the multilayer perception (MLP), which is a machine learning (ML) algorithm used in various fields, includes the uncontrollable growth of the number of total parameters, which may make MLP redundant in such high dimensions, and the uncontrollable growing stack of layers that ignores spatial information. Optimization algorithms were developed to determine the optimum number of parameters for MLP. Methods In this paper, the performances of the Genetic Algorithm (GA), Grasshopper Optimization Algorithm (GOA), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) are compared. The study also sought to determine the impact of sample size variations on these optimization algorithms. A dataset on the direct marketing campaigns of a Portuguese banking institution from the UCI Machine Learning Repository with a sample size of 4 521 was used. Synthetic Minority Oversampling Technique (SMOTE) was applied to balance the binary dependent variables for the training data across various sample sizes. Results Based on the classification accuracy, specificity, sensitivity, precision, F-score, and execution time, the MLP based on CMA-ES (CMA-ES-MLP) was identified as the best classifier overall, as it maintained high rates of these classification metrics and was the second fastest to train. CMA-ES-MLP with a training sample of 5 114 was our ideal classifier, and it competes well with the classifiers that have been built by previous studies that used the same dataset. Conclusions The study found no consistent increase or decrease in the classification performance of the algorithms as the sample size increased, and the metrics fluctuated rapidly across sample sizes. It is recommended that future studies be conducted to compare the best-performing classifiers identified in previous studies with the CMA-ES-MLP in this study under the same experimental conditions.