Predicting the On-The-Job Training Performance of IT Students on Virtual Internship Using Naïve Bayes

The student on-the-job training is one of the major concerns of the Higher Education Institution (HEI) in this time of pandemic. Virtual Internship was introduced and can be challenging to the students. This study focuses on data mining techniques to predict the performance of student on-the-job training in an online environment among IT students in Central Luzon State University. The researcher used Naive Bayes classification technique and 80 IT students are the respondent of the study. The performance of Naive Bayes algorithm using the WEKA tool 3. S.5 having a precision of 0.867 and a recall of 1.000 which is a high accuracy can be applied in predicting student performance in an online environment of every HEI for more efficient and effective on-the-job training performance of every student. This approach can help the HEI in developing student success in online work related performances. It will also give a positive perception that taking the on-the-job training in an online environment is the same as taking the actual working environment.