Around two hundred and fifty million individuals, with a major part of them being ladies influenced by diabetes. This number may ascend to 380 million by another decade. The sickness has been named as the fifth deadliest illness in the world with not a single inevitable fix to be seen. With the ascent of data innovation and proceeding with an approach into the restorative and medicinal services part, the instances of diabetes and their side effects all around are archived. Information mining is a buzz word separating concealed data from an enormous arrangement of database. It assists scientists in building large database in the area of biomedical engineering. The Pima Indian diabetes database was used for investigation purpose. In this paper an attempt has been made to study the effect of various classification and mining Techniques like Decision Tree, Naïve Bayes, SVM, Regression etc on the diagnosis of Type-2 diabetes.