Comparative Analysis of Machine Learning Models on Student Performance Data: Insights from Test Scores and Survey Data
Journal Title: European Journal of Teaching and Education - Year 2025, Vol 7, Issue 1
Abstract
With the increasing use of digital learning platforms, large volumes of student data have become available for analysis. This paper investigates how machine learning, learning analytics, and educational data mining can be utilized to gain insights into student performance. Various predictive modeling techniques, including Random Forest (RF), K-Nearest Neighbor (KNN), and Decision Trees (DT), are evaluated for their ability to forecast student test scores. Clustering algorithms like K-means are employed to identify patterns within the data. The study integrates these predictive models with survey data collected from undergraduate students at Heriot-Watt University Dubai, aiming to identify factors that influence academic outcomes. The research uses comparative analysis across different machine learning models which is applied to both the survey data and Kaggle test score data. The analysis reveals that linear regression is the most effective model for the Kaggle test score dataset, while K-means clustering provides the best insights from the survey data. The survey model is determined to be more comprehensive due to its inclusion of more predictors. Key metrics, such as accuracy scores, precision, recall, F1 score, and mean squared error, were calculated for both datasets to provide a quantitative overview, enabling a comparative evaluation of model performance and predictor effectiveness for both the datasets. The findings contribute to understanding how data-driven approaches can support educational decisions and interventions while addressing ethical considerations and inclusivity in educational settings.
Authors and Affiliations
Sanjana Sundararaman,Maheen Hasib,
Keywords
Related Articles
- EP ID EP760042
- DOI https://doi.org/10.33422/ejte.v7i1.1459
- Views 33
- Downloads 0
Using PLS Path Modelling in Education System: A Model to Measure the Academic Performance Score
Partial Least Square (PLS) was used the path modelling. Latent variables such as staff, institution (administration, number of enrolments, quality of laboratories, rooms, etc.), incentive applied for research and Academi...
The Predictive Effects of Reading Motivation Constructs and Reading Practice on Moroccan Fourth Graders Reading Comprehension Achievement: An Analysis of PIRLS 2011 Study
More than any other skill, reading proficiency is important to effectively navigating the school curriculum, shaping each individualâs trajectory through life, and actively taking part in broader society (Martin, Mulli...
A 2021 Online Workshop for the Review of Two Modules on Methodology for Using English as a Medium of Instruction in Rwanda: Opportunities and Challenges
Since the outbreak of the COVID-19 pandemic in Wuhan in China and its rapid spread around the globe, peopleâs life and work styles have changed. Governments have installed and implemented lockdowns, social distancing,...
Moral Development in Adolescents as A Key Indicator for The Prevention of Violent Behavior in Their Couples’ Relationships
Dating violence is a multidimensional and cross-cultural problem that in the last decade has extended worryingly to teenage age. The consequences are so serious and lasting over time that they cause serious psychological...
Teaching Strategies of the 21st Century Skills Adapted to the Local Needs
Evident is that fact that ICTs are at the core of fast-changing economy. However, ICTs in themselves do not create a knowledge-based economy. Innovation starts with people, making human capital within the workforce decis...