TY - JOUR T1 - Mining Student Data to Characterize Drop out Feature Using Clustering and Decision Tree Techniques AU - , K. Shyamala AU - , S.P. Rajagopalan JO - International Journal of Soft Computing VL - 2 IS - 1 SP - 150 EP - 156 PY - 2007 DA - 2001/08/19 SN - 1816-9503 DO - ijscomp.2007.150.156 UR - https://makhillpublications.co/view-article.php?doi=ijscomp.2007.150.156 KW - Data mining KW -decision trees KW -Clustering KW -drop out AB - Compared to traditional analytical studies that are often hindsight and aggregate, data mining is forward looking and is oriented to individual students. This study presents the work of data mining in predicting the drop out feature of students. This study applies decision tree technique to choose the best prediction and clustering analysis. The list of students who are predicted as likely to drop out from college by data mining is then turned over to teachers and management for direct or indirect intervention. ER -