The Role of Predictive Analytics in Personalizing Education: Tailoring Learning Paths for Individual Student Success

Literature Study

Lainjo, B. (2023) investigated the use of predictive analytics tools to assist schools in North America in retaining a greater number of students and reducing the number of students that drop out. Data mining techniques such as k-Nearest Neighbor, Neural Networks, Decision Trees, and Naive Bayes are utilized in order to categorize student dropout rates into distinct groups and encourage a greater number of students to continue their education. In the year 2022, Shafiq, D. and colleagues proposed the utilization of machine learning and predictive analytics as a means of identifying students in virtual learning environments who are likely to experience difficulties. The purpose of this study is to investigate the effectiveness of unsupervised machine learning approaches in comparison to supervised learning processes in identifying children who may be at risk.The authors Prasanth, A., and Alqahtani, H. (2023) desired to develop a prediction model that might identify early warning indicators of failure in college environments through the application of machine learning. It examined a variety of elements of student behavior, including academic achievement, engagement, participation in classes, and involvement on campus, among others. According to Kim, S. et al. (2022), who investigated several forms of data in order to forecast college dropout rates, they discovered that academic data had a significant impact on the accuracy with which machine learning models forecast graduation and dropout status. Machine learning techniques were utilized by Moon, M.H., et al. (2023) in order to identify parameters that may be utilized in the prediction of the dropout rate at four-year universities. The amount of money that each student spent on school supplies, according to their study budgets, the number of first-year students who registered, and the number of persons who found employment were all important variables.