Predictive analytics using data mining technique Dropout rates for students in correspondence and open courses are on increase. There is a need of analysis of factors causing increase in dropout rate. The discovery of hidden knowledge from the educational data system by the effective process of data mining technology to analyze factors affecting student drop out can lead to a better academic planning and management to reduce students drop out from the course, as well as can generate valuable information for decision making of stake holder to improve the quality of higher educational system. Data mining technique can be used for analysis and prediction. In this seminar I have used real data from a study center of Indira Gandhi National Open University. I have collected data from various sources like university database, survey form, etc. Various steps of mining is applied to deduce useful result. Various scenarios were compared and there accuracy was calculated. This study presents the work of data mining in predicting the drop out feature of students. This paper presents analysis of data set using data mining algorithms. After analysis the outcome will be the major factors that affect student dropping out of the open courses the most (dropout rate). Before applying classification algorithms some feature selection algorithms are also used so as to get refined prediction results. Such analysis and prediction information will help college management and teachers to make necessary changes for imparting better education. Mining of useful knowledge can be done by using many other mining techniques like association, clustering. Tool used for feature selection and mining is weka.