Estimation of conventional and innovative models for Rwanda's GDP per capita: A comparative analysis of artificial neural networks and Box–Jenkins methodologies

Abstract

This study aims to model the time series data of Rwanda's GDP per capita using the Box–Jenkins (BJ) approach as a conventional approach and artificial neural networks (ANNs) as an innovative approach. The BJ technique, which utilizes autoregressive moving average - ARMA or an integrated version of ARMA - ARIMA, has been applied, and it is found that the ARIMA (0,2,1) model is the best fit for Rwanda's GDP per capita. Moreover, three ANNs models (the long short-term model- LSTM, the generalized regression neural network- GRNN, and the multilayer perception - MLP) have been utilized for the dataset. It is shown that the MLP and GRNN models have outperformed the LSTM model and BJ approach in terms of statistical criteria. In addition, the LSTM model is not superior to the BJ model, except for the Mean Absolute Percentage Error (MAPE) value. Therefore, any inference that ANNs models will always be superior to traditional approaches would be misleading. It is necessary to evaluate the results cumulatively using both traditional and innovative methods and then come to a conclusion. Additionally, the study provides insights into the use of both BJ and ANNs approaches for modeling time series data of GDP per capita and highlights the potential of ANNs models for improving the prediction accuracy of GDP per capita. Decision-makers and policymakers may benefit in the future from these analyses and results including recommendations.