Commencing-Student Enrolment Forecasting Under Data Sparsity with Time Series Foundation Models

2026-02-12

AI Summary

This study addresses the challenges of forecasting undergraduate enrollment in higher education institutions, where data sparsity, short time series, and abrupt policy shifts hinder traditional methods—especially under small-sample conditions. To overcome these limitations, the authors propose a zero-shot time series foundation model (TSFM) framework that enables accurate predictions without institution-specific training. Key innovations include a leakage-proof, compact set of covariates, the introduction of a transferable Institutional Operating Condition Index (IOCI), and stabilized Google Trends–based demand proxies. The approach integrates rigorously time-aligned expanded-window backtesting with covariate-conditioned modeling. Empirical results demonstrate that the proposed method achieves performance comparable to established benchmarks in zero-shot settings, while exhibiting nuanced, heterogeneous effects across diverse student subpopulations and model architectures.

Technology Category

• Machine Learning: Other Foundations of Machine Learning
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty
• Search and Optimization: Other Foundations of Search & Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems

Abstract

Many universities face increasing financial pressure and rely on accurate forecasts of commencing enrolments. However, enrolment forecasting in higher education is often data-sparse; annual series are short and affected by reporting changes and regime shifts. Popular classical approaches can be unreliable, as parameter estimation and model selection are unstable with short samples, and structural breaks degrade extrapolation. Recently, TSFMs have provided zero-shot priors, delivering strong gains in annual, data-sparse institutional forecasting under leakage-disciplined covariate construction. We benchmark multiple TSFM families in a zero-shot setting and test a compact, leakage-safe covariate set and introduce the Institutional Operating Conditions Index (IOCI), a transferable 0-100 regime covariate derived from time-stamped documentary evidence available at each forecast origin, alongside Google Trends demand proxies with stabilising feature engineering. Using an expanding-window backtest with strict vintage alignment, covariate-conditioned TSFMs perform on par with classical benchmarks without institution-specific training, with performance differences varying by cohort and model.

Problem

• enrolment forecasting
• data sparsity
• time series foundation models
• structural breaks
• higher education

Innovation

• Time Series Foundation Models
• Zero-shot Forecasting
• Data Sparsity
• Institutional Operating Conditions Index
• Leakage-safe Covariates