PREDICTING SOFTWARE DEFECTS WITH ASSOCIATION MINING TO DISCOVER DEFECT PATTERN BY USING ABDP IJITMIS © I A E M E

ABSTRACT This paper presents an efficient problem solving approach and detecting defects at an early stage, which is based on the Action-Based Defect Predection(ABDP)and Feature Subset Selection (FSS). Factors causing defects vary according to the different attributes of a project, including the experience of the developers, the product complexity, the development tools and the schedule. The most significant challenge for a project manager is to identify actions that may incur defects before the action is performed. Actions performed in different projects may yield different results, which are hard to predict in advance. This approach will practically:(i) Accurately predicting actions that cause many defects by mining records of performed actions. (ii) To address this problem, the under-sampling is applied to the data set to increase the precision of predictions for subse-quence actions. (iii)It is applied to a business project, revealing that under-sampling with FSS successfully predicts the problematic actions during project execution. This method applies association rule mining to find out defect patterns, and multi-interval discretization to hold the persistent attributes of actions. The discovered patterns then can be applied to predict the defects generated by the following actions and take required corrective actions to avoid defects. In addition to improve software quality products, if two or more failure modes have the same RPN, it is possible to prioritize the failure modes with the help of FMEA and Risk Priority Code (RPC). If there is a tie situation in RPC, a more detailed selection can be done. The proposed technique is useful to industry project, generous exceptional prediction results and informative the efficiency of the proposed approach. The detected actions not only provide the information to avoid possible defects, but also facilitate the software process improvement