Abstract: The prediction of e-waste recovery scale is the basis for the government to formulate the development plan of circular economy and relevant subsidy policies, and for enterprises to evaluate the value of resource recovery and optimize production capacity. In this paper, the CH-X12 /STL-X framework for e-waste recycling scale prediction is proposed based on the idea of “Decomposition-ensemble”, considering that the seasonal data characteristics of the quarterly e-waste recycling scale data may lead to large prediction errors by using traditional single model and unstable prediction results. Firstly, the seasonal data characteristics of the time series of e-waste recovery scale are identified based on Canova-Hansen (CH) test, and then the time series suitable for seasonal decomposition is extracted with X12 or seasonal -trend decomposition procedure based on loess (STL) model for seasonal components. Then, the Holt-Winters model is used to predict the seasonal component, and the support vector regression (SVR) model is used to predict the other components. Finally, the linear sum of the prediction results of each component is used to obtain the final prediction result. The empirical results show that the proposed CH-X12/STL-X prediction framework can better meet the modeling requirements of time series prediction driven by different seasonal data characteristics and has better and more stable prediction performance than the traditional single models (Holt-Winters model, Seasonal Autoregressive Integrated Moving Average model, and SVR model).

Key words: e-waste; seasonal decomposition; integrated prediction; Data-Trait-Driven modeling