DESIGN AND IMPLEMENTATION OF STUDENTS ACADEMIC PERFORMANCE PREDICTION MODEL USING DECISION TREE CLASSIFIERS

ABSTRACT

Educational data mining is the process of applying data tools and techniques to analyze data at an educational institution. Educational institutions receive large amounts of data from studentsduring their duration inschool. However, this data most times remains underutilized and is of no benefit to the academic performance of the students. The success of any educational institution can be determined by the failure or success rate of the students. The proposed system uses educational data mining to analyze data in order to make predictions for student’s performance. The prediction will help the students and teachers to monitor the students’ performance in a systematic way so that the appropriate action can be taken to improve it where needed. For this prediction system, the total number of courses for the year will be cumulated and the focus will be on the mandatory courses as this has a higher impact on a student’s GPA. Classification (supervised learning) technique and decision tree algorithm will be applied on the data to predict their performance from their final exams. In this project, Weka (Waikato Environment for Knowledge Analysis) will be used for data preprocessing and Decision Tree Algorithm is used to create Decision Tree Classifier in Python with scikit-learn and visualize it graphically. The purpose for this is to ensure that we can feed any new data to classifier and it would be able to predict the right class accordingly.