Vol 6, No 4 (2018)
Can Machine Learning Improve Recession Prediction Accuracy?
Azhar Iqbal, Kyle Bowman
Abstract
This paper proposes a framework to utilize machine learning and statistical data mining tools in the economics/financial world with the goal of more accurately predicting recessions. Decision makers have a vital interest in predicting future recessions in order to enact appropriate policy. Therefore, to help decision makers, we raise the question: Does machine learning and statistical data mining improve recession prediction accuracy? Our first method examined over 500,000 variables as potential predictor variables for recession forecasting. Furthermore, to obtain the final logit/probit model specification, we ran 30 million different models. The selected model was then utilized to generate recession probabilities. The second method is the random forest approach, a famous class of machine learning tools. The third approach we employ is known as gradient boosting, a technique that also belongs in the machine learning family. Moreover, we built an econometric model that utilizes the yield curve as a recession predictor and employ that model as a benchmark. To test a model’s accuracy, we employ both in-sample and out-of-sample criteria. In our tests, the random forest approach outperforms all the other models (gradient boosting, statistical machine learning and the simple econometric model) in both the in-sample and out-of-sample situations. The gradient boosting model comes in second place, while the statistical data mining approach captures third. Furthermore, if we combine all four probabilities, then that method is still unable to beat the random forest’s prediction accuracy. That is, the random forest approach, alone, is the best. Our analysis proposes that machine learning can improve recession prediction accuracy. Moreover, our models suggest a less than 5% chance of a recession during the next 12 months.
Full text: 
PDF
Keywords
Recession Prediction; Machine Learning; Statistical Data Mining; Logit/Probit; Yield Curve.
Publication information
Volume 6, Issue 4
Year of Publication: 2018
ISSN: 1857 - 8721
Publisher: EDNOTERA
How to cite
Iqbal, A., Bowman, K.: Can Machine Learning Improve Recession Prediction Accuracy? Journal of Applied Economics and Business, Vol 6, No. 4, 16-34. (2018)