An Integrated Approach of K-Medoid and Logistic Regression for Forecasting of Student Performance

Students' academic performance is perilous for educational institutions because tactical programs can be prearranged in cultivating or maintaining enactment of the students for the duration of their period of studies in the institutions. The upsurge of student’s dropout rate in higher education is one of the significant problems in most organizations. The unearthing of hidden information from the educational data system by the operative process of data mining technique to investigate factors affecting student waster can lead to a healthier academic planning and administration to moderate students drop out frequency, as well as can apprise cherished information for outcome making of policy makers to mend the quality of higher educational system. In this paper, we consider issues of factors affecting prediction accuracy discussed about different techniques of data mining, machine learning which will predict the student performance index. In this paper we have proposed a prediction model which is integration of machine leaning (Logistic Regression) and k-medoid clustering (Data Mining Technique) algorithm for student performance prediction.