AI models forecast university enrollments even with sparse data

This paper introduces a framework using zero-shot Time Series Foundation Models (TSFMs) to forecast university enrollments, particularly when historical data is scarce or disrupted by structural changes. The researchers benchmarked these TSFMs against traditional methods, incorporating external data like Google Trends and an Institutional Operating Conditions Index (IOCI) to improve accuracy without needing specific institutional training. The findings indicate that while TSFMs can be competitive, their practical benefit depends on specific institutional characteristics and how covariates are designed. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Provides a transferable forecasting protocol for educational institutions facing data scarcity and instability.

RANK_REASON This is a research paper published on arXiv detailing a new framework for time series forecasting.

Read on arXiv cs.AI →

• Jittarin Jetwiriyanon
• Google Trends
• arXiv
• TSFM

• paper
• other