A1325
Title: Forecasting job market demand in Hong Kong using time series foundation models
Authors: Philip Yu - The Education University of Hong Kong (Hong Kong) [presenting]
Oscar Wong - The Education University of Hong Kong (Hong Kong)
Abstract: Timely labor market data is critical for economic policy, yet official job vacancy statistics in Hong Kong are published with a one-quarter delay. The aim is to investigate whether high-frequency online job postings (OJPs) can improve short-term vacancy forecasts. Amazon's Chronos-2 foundation model is benchmarked against traditional statistical, machine learning, and deep learning alternatives, demonstrating that a fine-tuned, covariate-enhanced Chronos-2 achieves superior forecasting accuracy. Feature importance analysis reveals that the predictive utility of such digital labor signals is highly sector-dependent.
