Self-Adaptive Scale Handling for Forecasting Time Series with Scale Heterogeneity

Time series forecasting (TSF) is crucial in various fields and has gained extensive research. However, most studies are conducted based on TS data with scale homogeneity. This paper proposes a self-Adaptive Scale-handling (AS) module to improve the performance of forecasting TS with scale heterogeneity. It consists of scale scaling selection and calibrating. We first calculate the priori scale factors of each time variable and then selectively calibrate the priori scale factors through neural networks. Hence, we can improve the performance of TSF algorithms by reducing scale restoration errors. We validate our method in collected industrial fund sales datasets from Ant Fortune and Alipay APP. Our AS module can easily be integrated into popular TSF models.