Latest Algorithms in Machine and Deep Learning Methods to Predict Retention Rates and Dropout in Higher Education: A Literature Review

Abstract

External factors, such as global impact, or internal factors, such as educational services or the quality of learning, can affect the Retention rate or Number of Dropouts (DO) of students in higher education. Higher education institutions must have a strategy to manage retention rates properly. They can take an initial approach by knowing the estimated retention rate or the number of DOs so they can anticipate it by determining the right strategy. Several researchers have researched retention prediction or DO using specific methods and algorithms. This literature review aims to provide an overview and analysis of the methods and algorithms used to predict retention rates or the Number of DOs of students in higher education and to know the latest trends in developing the algorithms used in predicting retention rates or DO. The method used in this research is the traditional literature review. We have identified Twenty-one articles according to the theme. From the article, there are 21 machine learning algorithms, 13 deep learning algorithms used, seven time-series algorithms, four feature selection algorithms, and three combinations of algorithms used. The review results show that deep learning algorithms provide higher accuracy values than machine learning algorithms, and the recent trend of using algorithms to predict retention levels or DO is towards using time series algorithms in deep learning methods.