Benchmark Analysis of Machine Learning Methods to Forecast the U.S. Annual Inflation Rate During a High-Decile Inflation Period

Rama K. Malladi ()
Additional contact information
Rama K. Malladi: California State University

Computational Economics, 2024, vol. 64, issue 1, No 13, 335-375

Abstract: Abstract Twenty-five machine learning (ML) methods and ordinary least squares regression (OLS) are trained to detect in-sample U.S. annual inflation rates up to a year in advance. The FRED-MD monthly dataset with 134 economic and financial variables from 1959 to April 2022 is used for training, validation, and forecasting. Out of these twenty-five ML methods, top-ten (by root mean square error or RMSE) are chosen to forecast the out-of-sample annual inflation rate. The ML methods are more accurate than the OLS in forecasting the annual inflation rate. The OLS does not appear in the top-10 list in any forecasting period. The ML methods robustly classify the labor market as the top factor in forecasting inflation. The labor market has a significantly higher impact on inflation than the housing or stock market.

Keywords: Inflation forecast; Financial econometrics; Machine learning (search for similar items in EconPapers)
JEL-codes: C5 C55 C58 E31 E37 (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10614-023-10436-w Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:kap:compec:v:64:y:2024:i:1:d:10.1007_s10614-023-10436-w

Ordering information: This journal article can be ordered from
http://www.springer. ... ry/journal/10614/PS2

DOI: 10.1007/s10614-023-10436-w

Access Statistics for this article

Computational Economics is currently edited by Hans Amman

More articles in Computational Economics from Springer, Society for Computational Economics Contact information at EDIRC.
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().