Soft-skill-based course recommender system framework (psychometric model + fitness functions + genetic algorithm)

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 2 claims rest on one study

Description

A recommender system that takes a student's course set as input, predicts expected soft skill proficiency with an ensemble of psychometric models, compares it to a targeted soft skill profile via score functions, aggregates the per-skill scores into a single fitness value, and uses genetic algorithms to search for the course set with the highest fitness. The article's stated aim is "to propose a recommender system framework, leveraging psychometric approaches in order to reduce the soft skills gap". It was illustrated on real data from three cohorts, producing recommendations for 172 different course sets.

Design Implications

Context

Requirements

• A targeted soft skill profile per specialisation
• Trained psychometric models predicting per-category probabilities for each soft skill
• A fitness function combining score functions and an aggregation method

Constraints

• Designed for short-term small-size datasets from higher education, where CF/CBF approaches lack sufficient interaction data
• Genetic algorithm hyper-parameters were chosen empirically through preliminary tests

Target Learners

• postgraduate students choosing specialisation courses

Learning Goals

• reaching targeted soft skill proficiency by the end of the program

Claims

• Recommendations Higher Fitness Than Actual Courses [+M]
• Recommendations Satisfy More Soft Skill Targets [+M]

Related Designs

Examples

-

Key Sources

• Luis Alberto Pinos Ullauri, Alexis Lebis, Abir Karami, Mathieu Vermeulen, Anthony Fleury, Wim Van den Noortgate. (2025). A Recommender System of Postgraduate Courses Based on Soft Skills: A Psychometric-inspired Approach. Int J Artif Intell Educ 35. https://doi.org/10.1007/s40593-025-00463-z

Page metadata

Field	Value
type	design
id	soft-skill-course-recommender-framework
title	Soft-skill-based course recommender system framework (psychometric model + fitness functions + genetic algorithm)
description	A recommender system that takes a student's course set as input, predicts expected soft skill proficiency with an ensemble of psychometric models, compares it to a targeted soft skill profile via score functions, aggr...
status	review
generated	by process:settle-candidates on 2026-10-28
trust	unverified — no one has confirmed this page's content
sources	1 — luis-alberto-pinos-ullauri-2025

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