The Catastrophe of Corruption in the Sustainability of Foreign aid: A Prediction of Artificial Neural Network Method in Indonesia

Abstract

The rising corruption levels in Indonesia are becoming a cause for concern and raise doubts about their impact on the stability of foreign aid in the country. Therefore, this study aims to predict the long-term viability of foreign aid in Indonesia based on international perceptions of corruption and corruption cases in the country. Data were obtained from World Governance Indicators, the Indonesian Ministry of Finance, and the World Bank, and the study used a backpropagation artificial neural network (ANN) for prediction. The results from ANN are compared to linear models and vector autoregression (VAR). The finding shows that ANN outperforms the other models based on the coefficient of determination and MSE values. Furthermore, it highlights the strong relationship between corruption perception and foreign aid sustainability with an R-value of 0.991. According to the ANN estimation, gratification has a significant impact on foreign aid. In response to this finding, the study recommends the Indonesian government take action to combat corruption in maintaining the international trust and ensuring the stability of foreign aid.