òòò½Íø Papers and Proceedings
ISSN 2574-0768 (Print) | ISSN 2574-0776 (Online)
Economic Measurement Lost in a Random Forest? A Case Study of Employment Data
òòò½Íø Papers and Proceedings
vol. 115,
May 2025
(pp. 68–72)
Abstract
Big data and machine learning (ML) offer transformative potential for economic measurement. This study evaluates the use of alternative employment data from a payroll processor to improve on timely measures of regional employment estimates, comparing ML methods—Lasso regression and Random Forest (RF)—to linear models. RF models show substantial improvements in cross-validation but struggle with extrapolation, particularly during the pandemic. At the county level, greater data variation aids prediction, though sampling errors complicate performance. These findings highlight ML's promise in improving economic statistics while emphasizing the need for careful model selection, robust evaluation metrics, and consideration of data-specific challenges.Citation
Dunn, Abe, Eric English, Kyle Hood, Lowell Mason, and Brian Quistorff. 2025. "Economic Measurement Lost in a Random Forest? A Case Study of Employment Data." òòò½Íø Papers and Proceedings 115: 68–72. DOI: 10.1257/pandp.20251103Additional Materials
JEL Classification
- C45 Neural Networks and Related Topics
- C55 Large Data Sets: Modeling and Analysis
- D22 Firm Behavior: Empirical Analysis
- L25 Firm Performance: Size, Diversification, and Scope
- M15 IT Management
- M51 Personnel Economics: Firm Employment Decisions; Promotions
- R23 Urban, Rural, Regional, Real Estate, and Transportation Economics: Regional Migration; Regional Labor Markets; Population; Neighborhood Characteristics