Examining the potential of machine learning for predicting academic achievement: A systematic review

• Main Authors: Nazir, M., Noraziah, Ahmad, Rahmah, M., Sharma, Aditi
• Format: Article
• Language: English
• Published: American Scientific Publishing Group (ASPG) 2023
• Subjects: QA75 Electronic computers. Computer science
• Online Access: http://umpir.ump.edu.my/id/eprint/38938/1/Examining%20the%20potential%20of%20machine%20learning%20for%20predicting%20academic%20achievement_FULL.pdf; http://umpir.ump.edu.my/id/eprint/38938/; https://doi.org/10.54216/FPA.130207; https://doi.org/10.54216/FPA.130207

Predicting student academic performance is a critical area of education research. Machine learning (ML) algorithms have gained significant popularity in recent years. The capability to forecast student performance empowers universities to devise an intervention strategy either at the beginning of a program or during a semester, which allows them to tackle any issues that may arise proactively. This systematic literature review provides an overview of the present state of the field under investigation, including the most commonly employed ML techniques, the variables predictive of academic performance, and the limitations and challenges of using ML to predict academic success. Our review of 60 studies published between January 2019 to March 2023 reveals that ML algorithms can be highly effective in predicting student academic performance. ML models can analyse various variables, including demographics, socioeconomic status, and academic history, to identify patterns and relationships that can predict academic performance. However, several limitations need to be addressed, such as the inconsistency in the variables used, small sample sizes, and the failure to consider external factors that may impact academic performance. Future research needs to address these limitations to develop more robust prediction models. Machine learning can fuse data from various sources like test scores like Coursera, edX & Open edX, Udemy, linkedin learning, learn words, and hacker’s rank platform etc, attendance, and online activity to help educators better understand student needs and improve teaching, can use for better decision. In conclusion, ML has emerged as a promising approach for predicting student academic performance in online learning environments. Despite the current limitations, the continued refinement of ML techniques, the use of additional variables, and the incorporation of external factors will lead to more robust models and greater accuracy in predicting academic performance.