A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses

Educational data mining (EDM) and learning analytics (LA) are widely applied to predict student performance, particularly in determining academic success or failure. This study presents the development of a scoring algorithm for the early identification of students at risk of failing science, techno...

Full description

Saved in:
Bibliographic Details
Main Authors: Vanja Čotić Poturić, Sanja Čandrlić, Ivan Dražić
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/18/4/177
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850183699869466624
author Vanja Čotić Poturić
Sanja Čandrlić
Ivan Dražić
author_facet Vanja Čotić Poturić
Sanja Čandrlić
Ivan Dražić
author_sort Vanja Čotić Poturić
collection DOAJ
description Educational data mining (EDM) and learning analytics (LA) are widely applied to predict student performance, particularly in determining academic success or failure. This study presents the development of a scoring algorithm for the early identification of students at risk of failing science, technology, engineering, and mathematics (STEM) courses. The proposed approach follows a structured process: First, educational data are collected, processed, and statistically analyzed. Next, numerical variables are transformed into dichotomous predictors, and their relevance is assessed using Cramér’s V measure to quantify their association with course outcomes. The final step involves constructing a scoring system that dynamically evaluates student performance over 15 weeks of instruction. Prospective validation of the model demonstrated excellent predictive performance (accuracy = 0.93, sensitivity = 0.95, specificity = 0.92), confirming its effectiveness in early risk detection. The resulting scoring algorithm is distinguished by its methodological simplicity, ease of implementation, and adaptability to different educational settings, making it a practical tool for timely interventions.
format Article
id doaj-art-8aecbdc1eacc4e75b5a5eb457bdfeb20
institution OA Journals
issn 1999-4893
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-8aecbdc1eacc4e75b5a5eb457bdfeb202025-08-20T02:17:14ZengMDPI AGAlgorithms1999-48932025-03-0118417710.3390/a18040177A Scoring Algorithm for the Early Prediction of Academic Risk in STEM CoursesVanja Čotić Poturić0Sanja Čandrlić1Ivan Dražić2Faculty of Informatics and Digital Technologies, University of Rijeka, 51000 Rijeka, CroatiaFaculty of Informatics and Digital Technologies, University of Rijeka, 51000 Rijeka, CroatiaFaculty of Engineering, University of Rijeka, 51000 Rijeka, CroatiaEducational data mining (EDM) and learning analytics (LA) are widely applied to predict student performance, particularly in determining academic success or failure. This study presents the development of a scoring algorithm for the early identification of students at risk of failing science, technology, engineering, and mathematics (STEM) courses. The proposed approach follows a structured process: First, educational data are collected, processed, and statistically analyzed. Next, numerical variables are transformed into dichotomous predictors, and their relevance is assessed using Cramér’s V measure to quantify their association with course outcomes. The final step involves constructing a scoring system that dynamically evaluates student performance over 15 weeks of instruction. Prospective validation of the model demonstrated excellent predictive performance (accuracy = 0.93, sensitivity = 0.95, specificity = 0.92), confirming its effectiveness in early risk detection. The resulting scoring algorithm is distinguished by its methodological simplicity, ease of implementation, and adaptability to different educational settings, making it a practical tool for timely interventions.https://www.mdpi.com/1999-4893/18/4/177educational data mininglearning analyticsacademic risk predictionscoring algorithmCramér’s Vearly intervention
spellingShingle Vanja Čotić Poturić
Sanja Čandrlić
Ivan Dražić
A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
Algorithms
educational data mining
learning analytics
academic risk prediction
scoring algorithm
Cramér’s V
early intervention
title A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
title_full A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
title_fullStr A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
title_full_unstemmed A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
title_short A Scoring Algorithm for the Early Prediction of Academic Risk in STEM Courses
title_sort scoring algorithm for the early prediction of academic risk in stem courses
topic educational data mining
learning analytics
academic risk prediction
scoring algorithm
Cramér’s V
early intervention
url https://www.mdpi.com/1999-4893/18/4/177
work_keys_str_mv AT vanjacoticpoturic ascoringalgorithmfortheearlypredictionofacademicriskinstemcourses
AT sanjacandrlic ascoringalgorithmfortheearlypredictionofacademicriskinstemcourses
AT ivandrazic ascoringalgorithmfortheearlypredictionofacademicriskinstemcourses
AT vanjacoticpoturic scoringalgorithmfortheearlypredictionofacademicriskinstemcourses
AT sanjacandrlic scoringalgorithmfortheearlypredictionofacademicriskinstemcourses
AT ivandrazic scoringalgorithmfortheearlypredictionofacademicriskinstemcourses