Systematic research on predictive models on students’ academic performance in higher education

• Main Authors: Azmee, N.A (Author), Mohamed, Z. (Author), Zulkifli, F. (Author)
• Format: Article
• Language: English
• Published: Blue Eyes Intelligence Engineering and Sciences Publication 2019
• Subjects: Classification; Clustering; Higher education; Regression; Students’ academic performance
• Online Access: View Fulltext in Publisher; View in Scopus
• ISBN: 22773878 (ISSN)
• ISSN: 22773878 (ISSN)
• DOI: 10.35940/ijrte.B1061.0782S319

In Malaysia, the students’ academic assessment has changed over time as it is now made to be more holistic. Predictive models used for educational data in Malaysia are still inadequate in giving a true picture of the students’ academic performance. The reason behind this is due to the lack of research in Malaysian context on predictive models and factors affecting students' academic achievement. Therefore, this study will conduct a systematic review on the literature, in order to identify the predictive methods for students’ academic performance in higher education. Through three major bases: WoS, Science Direct and IEEE Xplore, an extensive search was conducted to find any related articles from 2014 to 2018 that use "predict", "forecast", "academic performance", "student" and "higher education" keywords in their text. Initially, 195 articles were selected to be used in this review. However, through titles and abstracts’ filtering and screen processing, only 69 articles found to discuss on the predictive model for student's academic performance at higher education level. Based on extensive reading, the most widely used attributes in the predictive models is the academic process. While predictive models can be categorized into three, namely classification, cluster and regression, there are nine methods used by previous researchers in all categories. The most widely used category from previous studies was the classification, with 33 articles. This study has listed the advantages and disadvantages of each method based on the previous studies. This study also has identified the challenges and gaps faced by previous researchers in improving the existing models in the future. Among the challenges faced by the predictive models are the amount of data and assumptions that need to be followed before analysis can be made. In the future, the predictive models used for students’ academic performance should consider the latest assessments’ valuation method based on a modern educational system that emphasizes on soft skills, interpersonal skills and high-level thinking capabilities. © BEIESP.