To predict military spending in China based on ARIMA and artificial neural networks models

摘要

W artykule przedstawiono wyniki analizy dotycz?cej przewidywanych wydatków Chin na militaria, opracowanej na podstawie modelu autoregresji (ang. ARIMA) oraz sztucznych sieci neuronowych (ANN). Dok?adno?? predykcji oparta zosta?a na funkcji ?redniej warto?ci absolutnej procentowego uchybu. Badania wykazuj?, ?e model ARIMA ma wy?sz? dok?adno?? i stabilno?? ni? model oparty na ANN w odniesieniu do czterech, ró?nych okresów (1, 3, 5, 10 lat), przy czym dla ANN badanie wykonano dla czterech warto?ci dok?adno?ci predykcji.%This study takes the initiative to forecast China's military spending based on autoregressive integrated moving average (ARIMA) models and artificial neural networks (ANNs) models. The mean absolute percentage error (MAPE) approach is applied to measure prediction accuracy. The results indicate that these single variable ARIMA models show higher accuracy and stability than those made by the single variable ANNs models across the four time periods, namely the short term (1 year), the medium term (3 years), the medium-long term (5 years), and the long term (10 years). As to multiple variable ANNs models, the prediction accuracy of each model with different variables has advantages in different time periods. The highest accuracy for the long term predictions among all of the multivariate models is made by ANN2 including China's military spending and GDP. ANN3 including variables of China's military spending, GDP, and inflation rates illustrates the most accurate prediction for the short term and medium-long term, while ANN4 including China's military spending, GDP, inflation rates, and Taiwan's military spending shows the highest accuracy for the medium term prediction. This concludes the contributions of this study.