Skip to content

Cohort-relative z-score feature engineering

Research Method · All research methods
Evidence · 1 claim (1 for) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

This design pattern transforms raw behavioural and academic performance features (e.g., average grade, VLE resource access counts) into z-score standardised values relative to the learner's cohort, making them "more generic, contextually meaningful and comparable across different cohorts." The article states this conversion "converted the learner's absolute and mean values for a given feature into a form that captures the degree to which it deviates from the learner's cohort." The pattern increases descriptive power and model accuracy but trades off interpretability, which matters when features feed prescriptive feedback.

Accounts

  • Cohort-relative z-score feature engineering converts raw academic and behavioural features into course-agnostic values for predictive modelling: This design pattern transforms raw behavioural and academic performance features (e.g., average grade, VLE resource access counts) into z-score standardised values relative to the learner's cohort, making them "more generic, contextually meaningful and comparable across different cohorts." The article states this conversion "converted the learner's absolute and mean values for a given feature into a form that captures the degree to which it deviates from the learner's cohort." The pattern increases descriptive power and model accuracy but trades off interpretability, which matters when features feed prescriptive feedback. (Teo Susnjak (2024))

Claims

-

Key Sources

  • Teo Susnjak. (2024). Beyond Predictive Learning Analytics Modelling and onto Explainable Artificial Intelligence with Prescriptive Analytics and ChatGPT. Int J Artif Intell Educ 34:452–482. https://doi.org/10.1007/s40593-023-00336-3
Page metadata
Field Value
type research-method
id cohort-relative-z-score-feature-engineering
title Cohort-relative z-score feature engineering
description This design pattern transforms raw behavioural and academic performance features (e.g., average grade, VLE resource access counts) into z-score standardised values relative to the learner's cohort, making them "more generic, contextually meaningful and comparable across different cohorts." The artic
status review
generated by process:settle-candidates on 2026-10-28
trust unverified — no one has confirmed this page's content

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