Off to the Races: A Comparison of Machine Learning and Alternative Data for Predicting Economic Indicators
This chapter is a preliminary draft unless otherwise noted. It may not have been subjected to the formal review process of the NBER. This page will be updated as the chapter is revised.
Chapter in forthcoming NBER book Big Data for 21st Century Economic Statistics, Katharine G. Abraham, Ron S. Jarmin, Brian Moyer, and Matthew D. Shapiro
Timely alternative data sources such as credit card transactions and search query trends have become more readily available in recent years, while sophisticated machine learning (ML) techniques have enabled marked gains in predictive accuracy. These advances offer the benefit of revealing economic news earlier in the estimation cycle, reducing revisions, and improving estimate quality. But which combinations of data and ML techniques give the most accurate prediction of national economic activity? To answer this question, we conduct a prediction horse race using a one-step ahead model validation design to evaluate how each ML algorithm, data set, and variable selection method weighs on predictive accuracy. We test 73,884 model specifications, consider 1,180 variables drawn from both traditional and alternative sources, and predict 188 quarterly revenue and expenditure series for the services sector as published in the Quarterly Service Survey (QSS)—a key data set that accounts for nearly 80% of the revisions to Personal Consumption Expenditure for Services (PCE Services). Our results indicate that ensemble methods such as Random Forests afford the highest chance of reducing revisions. Relative to current national accounting methods, ensemble methods could reduce overall PCE revisions by 12% on average, with proportionally larger improvements among PCE sub-components. While alternative data are timelier, we find evidence that traditional data such as employment and lagged dependent variables contain relatively greater signaling power than alternative data; this finding demonstrates that more data does not necessarily translate into significantly better predictions.