Towards a Students’ Dropout Prediction Model in Higher Education Institutions Using Machine Learning Algorithms

Abstract

Using machine learning to predict students’ dropout in higher education institutions and programs has proven to be effective in many use cases. In an approach based on machine learning algorithms to detect students at risk of dropout, there are three main factors: the choice of features likely to influence a partial or total stop of the student, the choice of the algorithm to implement a prediction model, and the choice of the evaluation metrics to monitor and assess the credibility of the results. This paper aims to provide a diagnosis of machine learning techniques used to detect students’ dropout in higher education programs, a critical analysis of the limitations of the models proposed in the literature, as well as the major contribution of this arti-cle is to present recommendations that may resolve the lack of global model that can be generalized in all the higher education institutions at least in the same country or in the same university.

Implementing a Risk Assessment System of Electric Welders’ Muscle Injuries for Working Posture Detection with AI Technology

“…Machine learning is a branch of the AI system that predicts task output values from given input data [12]. An ML system engages in the type of experiential learning associated with human intelligence while also being able to learn and improve its analyses using computational algorithms [12][13][14][15][16]. ML can be applied in ergonomics, which focuses on improving human comfort, safety, and performance.…”

Ameliorating Heart Diseases Prediction using Machine Learning Technique for Optimal Solution

“…In [2], the authors presented a machine-learning based approach to predict the heart disease adopting the Cleveland heart disease database. Several ML approaches such as classification and regression are employed, including "Random Forest, Decision Tree, and Hybrid Model".…”

“…Using machine learning techniques, a disease can be diagnosed more accurately. A variety of classification algorithms are available to predict diseases such as liver disease, heart disease, diabetes, and tumors based on machine learning concepts; similarly, "regression algorithms, Random Forest, Lasso, and Logistic Regression" are used in the medical field [2], [3].…”

Design of a Machine Learning Model to Predict Student Attrition

“…As higher education becomes increasingly populated, tracking the performance of each student and identifying students at risk of failing or dropping out is almost impossible without IT systems. However, ML methods, which can be considered part of artificial intelligence (AI), can help address this problem [13][14][15][16] [21] [23] [26]. Predictive models can be used to effectively identify students at risk of dropping out, but this is only possible with well-designed models.…”