利用机器学习加强通胀预测  

Enhanced Inflation Forecasts with Machine Learning

作　　者：刘洋 潘然 许睿 田振 周正铭 LIU Yang;PAN Ran;XU Rui

机构地区：[1]IMF(国际货币基金组织)

出　　处：《新金融》2025年第4期59-66,共8页New Finance

摘　　要：自2020年以来,由于供应链中断和新冠疫情后的经济不确定性,预测通货膨胀已成为中央银行面临的一大挑战。机器学习模型可以通过纳入更广泛的变量、允许非线性关系以及关注样本外预测表现来提高预测准确性。在本文中,我们应用机器学习(ML)模型来预测日本近期的核心通胀率。日本是一个具有挑战性的案例,因为通胀在2022年之前一直处于低位,而现在已经上升到了四十年来前所未见的水平。我们对大量预测因子应用了四种机器学习模型以及两种基准模型。对于2023年,两种惩罚回归模型系统性地优于基准模型,其中LASSO提供了最准确的预测。2022年后预测通货膨胀的有效预测变量包括家庭通货膨胀预期、入境旅游人数、日元汇率和产出缺口。Forecasting inflation has become a major challenge for central banks since 2020,due to supply chain disruptions and economic uncertainty post-pandemic. Machine learning models can improve forecasting performance by incorporating a wider range of variables,allowing for non-linear relationships,and focusing on out-of-sample performance. In this paper,we apply machine learning(ML) models to forecast near-term core inflation in Japan post-pandemic. Japan is a challenging case,because inflation had been muted until 2022 and has now risen to a level not seen in four decades. Four machine learning models are applied to a large set of predictors alongside two benchmark models. For 2023,the two penalized regression models systematically outperform the benchmark models,with LASSO providing the most accurate forecast.Useful predictors of inflation post-2022 include household inflation expectations,inbound tourism,exchange rates,and the output gap.

关 键 词：核心通货膨胀 预测 机器学习模型 LASSO 日本 

分 类 号：F822.5[经济管理—财政学]