Explainable inflation forecasts by machine learning models

作者：

Highlights：

• The form of the forecast equation for factor models is constructed by ML models.

• RF delivers regularly consistent performance without using a factor model.

• Tree-based models exhibit superior performance with a high number of predictors.

• Explainable inflation forecasts are produced by ML models.

摘要

•The form of the forecast equation for factor models is constructed by ML models.•RF delivers regularly consistent performance without using a factor model.•Tree-based models exhibit superior performance with a high number of predictors.•Explainable inflation forecasts are produced by ML models.

论文关键词：Machine learning,Inflation forecasting,Factor models,Model interpretability,Tree-based models,Shapley values

论文评审过程：Received 2 April 2022, Revised 3 June 2022, Accepted 23 June 2022, Available online 28 June 2022, Version of Record 1 July 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.117982