A HYBRID STACKING ENSEMBLE FRAMEWORK FOR EMPLOYMENT PREDICTION PROBLEMS

In this paper we put forward a hybrid stacking ensemble approach for classifiers which is found to be a better choice than selecting the best base level classifier. This paper also describes and compares various data mining methodologies for the domain called employment prediction. The proposed application helps the prospective students to make wise career decisions. A student enters his Entrance Rank, Gender (M/F), Sector (rural/urban) and Reservation category. Based on the entered information the data mining model will return which branch of study is Excellent, Good, Average or poor for him/her. Various data mining models are prepared, compared and analyzed.