Predicting Non Farm Employment

TL;DR

This paper develops machine learning models to accurately predict U.S. nonfarm employment figures before official reports, achieving high accuracy and directional correctness, aiding market analysis and decision-making.

Contribution

It introduces a novel approach using feature extraction and ensemble machine learning models to forecast nonfarm employment with unprecedented accuracy.

Findings

R2 of 0.9985 indicating excellent predictive performance

99.99% directional accuracy on out-of-sample data

Effective use of aggregated payroll data for employment prediction

Abstract

U.S. Nonfarm employment is considered one of the key indicators for assessing the state of the labor market. Considerable deviations from the expectations can cause market moving impacts. In this paper, the total U.S. nonfarm payroll employment is predicted before the release of the BLS employment report. The content herein outlines the process for extracting predictive features from the aggregated payroll data and training machine learning models to make accurate predictions. Publically available revised employment report by BLS is used as a benchmark. Trained models show excellent behaviour with R2 of 0.9985 and 99.99% directional accuracy on out of sample periods from January 2012 to March 2020. Keywords Machine Learning; Economic Indicators; Ensembling; Regression, Total Nonfarm Payroll