A novel unemployment rate forecasting method based on fuzzy information granules and GM(1,1) model

Granular computing is a novel method to solve complex tasks in the context of big data by simulating human problem-solving thinking, abstracting complex problems and dividing them into several simpler problems (i.e., granulation), which helps to better analyze and solve problems. In order to improve the accuracy of forecasting unemployment rates, this paper introduces the granulation idea of granular computing into the time series analysis of unemployment rates. Therefore, a novel method based on fuzzy information granules (FIGs) and grey system theory, namely FIG-GM(1,1) model, is proposed. This method not only reduces the dimensionality of the problem and computational complexity but also effectively reduces cumulative errors. In empirical analysis, three different performance indicators, mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE), and seven comparative models are used to evaluate the forecasting performance of our proposed model. The empirical results indicate that the MAE, MAPE, and RMSE values of the FIG-GM(1,1) model are significantly lower than those of other models, indicating that the FIG-GM(1,1) model has better forecasting performance compared to other models.