Prediction Model for Students' Performance in Java Programming with Course-content Recommendation System

Comparative analysis among different data mining algorithm for attribute selection and classification was conducted on this two-phase study which aimed to predict the students’ performance in Java Programming and be able to generate recommendations. Processes in Knowledge Discovery in Database (KDD) was followed in finding patterns among the historical data. Logistic Regression and Correlation-based Feature Selection was used for finding significant predictors. Classifiers such as CHAID, Exhaustive CHAID, CRT, QUEST, J48, BayesNet, NaïveBayes and JRip were implemented and it was found out that J48, on the context of this study, has the most straightforward rules set and the highest percentage of prediction. For the second phase evolutionary prototyping implemented through Ruby on Rails was done to develop a web-based examination module that will determine the students’ index of learning style and to assess their prior knowledge in Java. A course-content recommendation presenting the learners’ strengths and weaknesses in the subject with suggested method of learning style will be automatically generated by the system.