Predictive analytic models of student success in higher education

Abstract

Purpose Many higher education institutions are investigating the possibility of developing predictive student success models that use different sources of data available to identify students that might be at risk of failing a course or program. The purpose of this paper is to review the methodological components related to the predictive models that have been developed or currently implemented in learning analytics applications in higher education. Design/methodology/approach Literature review was completed in three stages. First, the authors conducted searches and collected related full-text documents using various search terms and keywords. Second, they developed inclusion and exclusion criteria to identify the most relevant citations for the purpose of the current review. Third, they reviewed each document from the final compiled bibliography and focused on identifying information that was needed to answer the research questions Findings In this review, the authors identify methodological strengths and weaknesses of current predictive learning analytics applications and provide the most up-to-date recommendations on predictive model development, use and evaluation. The review results can inform important future areas of research that could strengthen the development of predictive learning analytics for the purpose of generating valuable feedback to students to help them succeed in higher education. Originality/value This review provides an overview of the methodological considerations for researchers and practitioners who are planning to develop or currently in the process of developing predictive student success models in the context of higher education.

Utilizing Student Time Series Behaviour in Learning Management Systems for Early Prediction of Course Performance

“…Examining the methods for predictive analytics in higher education is another common theme in the literature. For example, most review papers in this area (e.g., Cui et al, 2019;Shahiri & Husain, 2015) have identified the most commonly used machine learning classifiers, such as logistic regression, decision tree, naïve Bayes, support vector machine, neural networks, and k-nearest neighbours. In addition, many studies on predictive analytics compared the prediction performance between different machine learning classifiers.…”

“…Despite the success of these methods and their variants, using machine learning techniques for predictive modelling often requires many attempts at data preprocessing and feature engineering since structured datasets are often required for most machine learning classifiers. Not many studies have explicitly reported how they preprocessed data and extracted features (Cui et al, 2019), and there is no explicit guidance on how to do data pre-processing and feature engineering. This may be because different datasets require different pre-processing procedures, and the selection of features is often arbitrarily decided by how researchers think of the potential factors influencing learning outcomes.…”

“…Given the common use of the LMS in higher education and its importance for teaching and learning, a large body of studies on predictive analytics have used LMS data together with student information from other sources to predict academic performance. In their review, Cui et al (2019) identified several major student-level data sources used in predictive analytics literature, including intermediate course performance, like quiz grades (e.g., Luo, Koprinska, & Liu, 2015), student behaviours in LMSs (e.g., Romero et al, 2013), survey data on socio-emotional variables (e.g., Guarín, Guzmán, & González, 2015), demographic information (e.g., Evale, 2016), and academic history (e.g., Ochoa, 2016). Studies that utilized multiple data sources often showed a high classification accuracy rate.…”

“…According to a review by Cui, Chen, Shiri, and Fan (2019), the number of publications on predictive learning analytics (PLAs) in higher education has dramatically increased in the past ten years. Given the ever-expanding developments in data science techniques, more researchers, senior administrators, and educators have realized the potential of data available in different educational systems for improving educational outcomes.…”

A System for Supporting the Adoption of Pedagogical Decisions based on an Assessment of Ownership of Strategies

“…An adequate student model is a condition for making the right pedagogical decisions. In the review [4], the authors identify methodological strengths and weaknesses of current predictive learning analytics applications and provide the most up-to-date recommendations on predictive model development, use and evaluation. The study described in the article [5] provides an overview of the progress made to date in learning analytics, that uses techniques, methods, and algorithms that allow the user to discover and extract patterns in stored educational data, with the purpose of improving the teaching-learning process.…”