Nowcasting Recessions using the SVM Machine Learning Algorithm

TL;DR

This paper applies Support Vector Machines to real-time recession nowcasting, demonstrating high predictive accuracy and providing implementation guidance for economic and financial applications.

Contribution

It introduces SVM as a novel tool for nowcasting recessions, with detailed implementation for practical use in economics.

Findings

SVM achieves excellent predictive performance for recession nowcasting.

The method provides timely detection of recession onsets and recoveries.

Implementation details facilitate adoption in economic forecasting.

Abstract

We introduce a novel application of Support Vector Machines (SVM), an important Machine Learning algorithm, to determine the beginning and end of recessions in real time. Nowcasting, "forecasting" a condition about the present time because the full information about it is not available until later, is key for recessions, which are only determined months after the fact. We show that SVM has excellent predictive performance for this task, and we provide implementation details to facilitate its use in similar problems in economics and finance.