Forecasting Labor Markets with LSTNet: A Multi-Scale Deep Learning Approach
Abstract
We present a deep learning approach for forecasting short-term employment changes and assessing long-term industry health using labor market data from the U.S. Bureau of Labor Statistics. Our system leverages a Long- and Short-Term Time-series Network (LSTNet) to process multivariate time series data, including employment levels, wages, turnover rates, and job openings. The model outputs both 7-day employment forecasts and an interpretable Industry Employment Health Index (IEHI). Our approach outperforms baseline models across most sectors, particularly in stable industries, and demonstrates strong alignment between IEHI rankings and actual employment volatility. We discuss error patterns, sector-specific performance, and future directions for improving interpretability and generalization.
Keywords
Cite
@article{arxiv.2507.01979,
title = {Forecasting Labor Markets with LSTNet: A Multi-Scale Deep Learning Approach},
author = {Adam Nelson-Archer and Aleia Sen and Meena Al Hasani and Sofia Davila and Jessica Le and Omar Abbouchi},
journal= {arXiv preprint arXiv:2507.01979},
year = {2025}
}
Comments
Undergraduate senior project, University of Houston, Department of Computer Science