Improving time series forecasting via nonlinear trend-adjusted tree-based models

초록

Tree-based machine learning models have limitations that despite their strong forecasting performance, they are vulnerable to extrapolation outside the distribution of data with a trend. To address this issue, this study proposes a two-step forecasting procedure in which the machine learning model is applied to the residuals after removing the trend from the time series. First, the global nonlinear trend component is separated through regression, and the residuals are extracted which may include autocorrelation and seasonality. After that, the residuals are modeled using Random Forest or XGBoost which are tree-based machine learning models. In the last forecasting step, the separated nonlinear trend is recombined. The simulation experiment uses data from the M3 and M4 competition data and compares the proposed method with a standalone machine learning model without the trend adjustment to evaluate performance. This study proposes a method to combine trend decomposition with machine learning models for time series forecasting and discusses how effective it can enhance forecasting accuracy and computation effciency.

키워드