Defect in software systems continue to be a major problem. High quality of software is ensured by Software reliability and Software quality assurance. A software defect causes software failure in an executable product. A variety of software fault predictions techniques have been proposed, but none has proven to be consistently accurate. The objective in the construction of models of software error prediction is to use measures that may be obtained relatively early in the software development life cycle to provide reasonable initial estimates of quality of an evolving software system. Here various data mining classification and prediction techniques viz. Neural Network (NN), Naïve Bayes, k-Nearest Neighbour (kNN) have been analysed and compared for software defect prediction model development. For this DATATRIEVETM project carried out at Digital Engineering, Italy has been used to validate the algorithm. The results showed that model using NN classification technique was a better prediction model.