The 2021–2022 surge in US inflation was unanticipated by the Survey of Professional Forecasters (SPF) and other macroeconomists and institutions. This study assesses whether nascent deep learning frameworks and methods more accurately project recent core personal consumption expenditures inflation. We create a recurrent neural network (RNN) to forecast long-term inflation, and after training on 60 years of quarterly data, the model outperforms the SPF and projects a spike in inflation similar to that of recent years. We compare the model's performance with and without COVID-19–specific data and discuss some implications of our findings for economic forecasting in global crises.

中文翻译：

---

使用深度（机器）学习来预测 COVID-19 时代的美国通胀

专业预测师调查 (SPF) 和其他宏观经济学家和机构没有预料到 2021 年至 2022 年美国通胀飙升。这项研究评估了新兴的深度学习框架和方法是否可以更准确地预测近期的核心个人消费支出通胀。我们创建了一个循环神经网络 (RNN) 来预测长期通胀，经过 60 年季度数据的训练，该模型的表现优于 SPF，并预测通胀峰值与近年来类似。我们比较了模型在有和没有 COVID-19 特定数据的情况下的表现，并讨论了我们的研究结果对全球危机中经济预测的一些影响。