Card forecasts for M4

被引:19
|
作者
Doornik, Jurgen A. [1 ,2 ]
Castle, Jennifer L. [2 ,3 ]
Hendry, David F. [1 ,2 ]
机构
[1] Univ Oxford, Oxford Martin Sch, Nuffield Coll, Oxford, England
[2] Univ Oxford, Oxford Martin Sch, Inst New Econ Thinking, Oxford, England
[3] Univ Oxford, Oxford Martin Sch, Magdalen Coll, Oxford, England
关键词
Automatic forecasting; Calibration; Forecast intervals; Regression; M4; Seasonality; Software; Time series; Unit roots;
D O I
10.1016/j.ijforecast.2019.03.012
中图分类号
F [经济];
学科分类号
02 ;
摘要
The M4 forecast competition required forecasts of 100,000 time series at different frequencies. We provide a detailed description of the calibrated average of Rho and Delta (Card) forecasting method that we developed for this purpose. Delta estimates a dampened trend from the growth rates, while Rho estimates an adaptive but simple autoregressive model. Calibration estimates a more elaborate autoregressive model, treating the averaged forecasts from Rho and Delta as if they were observed. The proposed method is easy to understand, combining very fast execution with an excellent forecast performance. (C) 2019 The Authors. Published by Elsevier B.V. on behalf of International Institute of Forecasters.
引用
收藏
页码:129 / 134
页数:6
相关论文
共 50 条