Exploratory unsupervised clustering methodology for identifying at-risk student profiles from pre-admission data

Research Method · All research methods
Evidence · 3 claims (2 for, 1 mixed) · 1 study (1 associational), q2 · 0 of 1 report an effect size · 3 claims rest on one study

Description

The article develops an exploratory, unsupervised methodology that applies clustering to university pre-admission data to find latent structures without predefined labels. "The process involves three main phases (see Fig. 1): Data Preparation, Experimentation and Analysis of the Selected Models." Model selection combines internal validation (Silhouette, Davies-Bouldin, Calinski-Harabasz), association with outcomes (Cramér's V), and cluster quality (purity, entropy) via a composite score. It is positioned as an alternative to deductive, theory-driven and supervised approaches.

Accounts

• Exploratory unsupervised clustering methodology for identifying at-risk student profiles from pre-admission data: The article develops an exploratory, unsupervised methodology that applies clustering to university pre-admission data to find latent structures without predefined labels. "The process involves three main phases (see Fig. 1): Data Preparation, Experimentation and Analysis of the Selected Models." Model selection combines internal validation (Silhouette, Davies-Bouldin, Calinski-Harabasz), association with outcomes (Cramér's V), and cluster quality (purity, entropy) via a composite score. It is positioned as an alternative to deductive, theory-driven and supervised approaches. (Fabian Santiago-Muñoz et al. (2025))

Claims

• Pre-admission data (2018–2022) contain sufficient information to identify early patterns of dropout or course failure in first-year engineering mathematics subjects [+M]
• The Gaussian Mixture algorithm achieved optimal clustering solutions in four of six scenarios, while no evaluated algorithm yielded satisfactory results in the remaining two [+M]
• The choice of normalization technique influences clustering outcomes, so multiple normalization approaches should be tested in cluster analysis [~M]

Related Research Methods

-

Key Sources

• Fabian Santiago-Muñoz, Mikel Larrañaga, Jon A. Elorriaga, Ana Arruarte. (2025). Identification of Patterns to Prevent the Failure of Engineering Students. Int J Artif Intell Educ 35:3356–3405. https://doi.org/10.1007/s40593-025-00502-9

Page metadata

Field	Value
type	research-method
id	exploratory-unsupervised-clustering-methodology-for-identifying-at-risk-student-profiles-f
title	Exploratory unsupervised clustering methodology for identifying at-risk student profiles from pre-admission data
description	The article develops an exploratory, unsupervised methodology that applies clustering to university pre-admission data to find latent structures without predefined labels.
status	review
generated	by process:settle-candidates on 2026-10-27
trust	unverified — no one has confirmed this page's content

Frontmatter is the page's machine-readable record — see the Schema & Guide.