Improving Academic Advising in Engineering Education with Machine Learning Using a Real-World Dataset - Article

Aug 3, 2026

Upload by Aurora

Academic advising is often handled by faculty-student advisors who must support large numbers of learners quickly, making the process inefficient and increasing the chance of incorrect qualification choices. This study uses a real-world dataset with student records across four engineering disciplines from a South African public university (2016–2017) to predict performance and recommend suitability for extended versus mainstream programmes. A three-step pipeline covers preprocessing, feature-importance selection, and model training with evaluation, addressing imbalance, bias, and ethical concerns. Results show that removing demographic attributes reduces bias, while mathematics, physical sciences, and admission point scores are key predictors, enabling accurate guidance.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages23

Reading Time58 min

AccessFree to download

Abstract

Introduction

Academic advising in engineering education

Motivation and challenges (dropout and low graduation rates)

algorithms Article Improving Academic Advising in Engineering Education with Machine Learning Using a Real-World Dataset Mfowabo Maphosa 1, Wesley Doorsamy 2, * and Babu Paul 1 Citation: Maphosa, M.; Doorsamy, W.; Paul, B. Improving Academic Advising in Engineering Education with Machine Learning Using a Real-World Dataset. Algorithms 2024, 17, 85. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)a17020085 Academic Editor: Shengkun Xie Received: 14 December 2023 Revised: 9 February 2024 Accepted: 16 February 2024 Published: 18 February 2024 Copyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Institute for Intelligent Systems, University of Johannesburg, Johannesburg 2092, South Africa; [201312940@student.uj.ac.za](201312940@student.uj.ac.za) (M.M.); [bspaul@uj.ac.za](bspaul@uj.ac.za) (B.P.) 2 School of Electronic and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UK * [Correspondence: w.doorsamy@leeds.ac.uk](Correspondence: w.doorsamy@leeds.ac.uk) Abstract: The role of academic advising has been conducted by faculty-student advisors, who often have many students to advise quickly, making the process ineffective. The selection of the incorrect qualification increases the risk of dropping out, changing qualifications, or not finishing the qualification enrolled in the minimum time. This study harnesses a real-world dataset comprising student records across four engineering disciplines from the 2016 and 2017 academic years at a public South African university. The study examines the relative importance of features in models for predicting student performance and determining whether students are better suited for extended or mainstream programmes. The study employs a three-step methodology, encompassing data pre-processing, feature importance selection, and model training with evaluation, to predict student performance by addressing issues such as dataset imbalance, biases, and ethical considerations. By relying exclusively on high school performance data, predictions are based solely on students’abilities, fostering fairness and minimising biases in predictive tasks. The results show that removing demographic features like ethnicity or nationality reduces bias. The study’s findings also highlight the significance of the following features: mathematics, physical sciences, and admission point scores when predicting student performance. The models are evaluated, demonstrating their ability to provide accurate predictions. The study’s results highlight varying performance among models and their key contributions, underscoring the potential to transform academic advising and enhance student decision-making. These models can be incorporated into the academic advising recommender system, thereby improving the quality of academic guidance. Keywords: academic advising; engineering education; real-world datasets; classification; bias in algorithms; machine learning; predicting student performance 1. Introduction Low graduation rates in engineering result in the need for more human capital for the industry, which translates to a shortage of skilled engineers [1] . South Africa is experiencing increased demand for engineering graduates as it looks to expand its infrastructure and technological capabilities. This demand is exacerbated by challenges in engineering education, such as high dropouts, low graduation rates, and the need to improve the quality of engineering education. With this demand, educational institutions in the country need help addressing challenges related to low graduation rates, as the situation hinders the industry’s growth. The low graduati

FAQs

Why can current academic advising become ineffective for engineering students?

Advisors often manage many students simultaneously, which can lead to rushed decisions and ineffective guidance. Incorrect qualification selection increases risks such as dropout, switching qualifications, or not completing within the minimum time.

What data and setting does the study use to support its machine-learning approach?

The research uses a real-world dataset of student records across four engineering disciplines from 2016 and 2017 at a public South African university.

How does the study address bias and ethical concerns in predictive modeling?

It includes a methodology that explicitly considers dataset imbalance, biases, and ethical considerations. Predictions rely exclusively on high school performance data, and the removal of demographic features like ethnicity or nationality reduces bias.

Aug 3, 2026

Upload by Aurora