ANALYSIS OF STUDENT PERFORMANCE FORECAST USING DATA MINING TECHNIQUES

Abstract

Data mining is a study of classification, association, prediction, clustering of data for the various field. Classification deals with static data in other terms it is supervised learning. Clustering is a non-supervised techniques used to take decision in a particular problem. Data mining is based on complex algorithms that allow for the segmentation of data to identify patterns and trends, detect anomalies, and predict the probability of various situational outcomes. Predictive analytics is an area of statistics. It deals with extracting information from data and using it to predict trends and behavior patterns. Education plays vital role to develop our nation. In this, there is a lot of research carried out in the field of education but no one is predict students pass rates. Here our research deals with student pass rates prediction using optimized Support Vector Machine (SVM) algorithm and Decision Tree (DT) algorithm.
We propose a new concept: features dependency algorithm, CART algorithm and machine learning algorithm to analysis relationship between the set of student features. And we also collect online and offline data of students from other schools and by using this algorithm we predict the student pass rates in blended learning. The purpose is to providing assistance to students who have greater difficulties in their studies and students who are at risk of graduating through data mining techniques. The result shows that to identify the week performance of the student and improve their performance by using this algorithm.