Detecting Of Software Bugs In Source Code Using Data Mining Approach

Abstract

In a large software system knowing which files are most likely to be fault-prone is valuable information for project managers. They can use such information in prioritizing software testing and allocating resources accordingly. However, our experience shows that it is difficult to collect and analyze fine grained test defects in a large and complex software system. On the other hand, previous research has shown that companies can safely use cross-company data with nearest neighbor sampling to predict their defects in case they are unable to collect local data. In this paper the discussion is done to predict software bugs in the source code by using data mining approach by training the models that are perfect and that are defect. In our experiments we used ranking method (RM) as well as nearest neighbor sampling for constructing method level defect predictors. Our results suggest that, for the analyzed projects, at least 70% of the defects can be detected by inspecting only (i) 4% of the code using a Naïve model, (ii) 6% of the code using RM framework.

Keywords: Testing, Defect predictors, Software bugs, Training, Ranking method

View PDF