Variables identification for Students Performance Prediction

Abstract

Student's performance analysis has taken a leap of faith in past two years when the delivery mode was shuttling between online and offline. Various factors which are significantly affecting student's performance are now newly to be researched and identified. Its very important to not only consider and study the effect of various academic factors but also socio-economic factors are needed to analyzed. Predictive analytics has shown its capabilities in efficiently predicting results in wide areas of application including academics. This analysis and prediction is most crucial in the developing country like India, where the published rate of retention of students at university level considered very low. In this research, the academic and socio-economic details collected from student through survey. Further efficacy of various machine-learning algorithms assessed by running these algorithms on survey data. The findings demonstrate that some machine learning algorithms may create accurate predictive models using historical data on student retention.