Macroeconomic forecasting using factor models and machine learning: an application to Japan
Macroeconomic forecasting using factor models and machine learning: an application to Japan
复制标题
DOI：
10.1016/j.jjie.2020.101104
复制
发表时间：
2020-12-01
影响因子：
2.9
通讯作者：
Shintani, Mototsugu
中科院分区：
文献类型：
--
作者：
Maehashi, Kohei;Shintani, Mototsugu
我们对因子模型和机器学习进行了深入的比较分析，以预测日本宏观经济时间序列。我们的主要结果可以概括如下。首先，在许多情况下，因子模型和机器学习比传统的AR模型表现得更好。其次，机器学习方法做出的预测在中长期预测期内表现得特别好。第三，机器学习的成功主要来自于变量的非线性和交互作用，这表明了非线性结构在预测日本宏观经济序列中的重要性。第四，因素模型和机器学习的组合预测效果优于单独的因素模型或机器学习；对于常见因素，机器学习方法被发现在组合预测中是有用的。
We perform a thorough comparative analysis of factor models and machine learning to forecast Japanese macroeconomic time series. Our main results can be summarized as follows. First, in many instances, factor models and machine learning perform better than the conventional AR model. Second, predictions made by machine learning methods perform particularly well for medium to long forecast horizons. Third, the success of machine learning mainly comes from the nonlinearity and interaction of variables, which suggests the importance of nonlinear structure in predicting the Japanese macroeconomic series. Fourth, the composite forecast of factor models and machine learning performs better than factor models or machine learning alone; and machine learning methods applied to common factors are found to be useful in the composite forecast.