Prediction of software development faults in PL/SQL files using neural network models

Abstract

Database application constitutes one of the largest and most important software domains in the world. Some classes or modules in such applications are responsible for database operations. Structured Query Language (SQL) is used to communicate with database middleware in these classes or modules. It can be issued interactively or embedded in a host language. This paper aims to predict the software development faults in PL/SQL files using SQL metrics. Based on actual project defect data, the SQL metrics are empirically validated by analyzing their relationship with the probability of fault detection across PL/SQL files. SQL metrics were extracted from Oracle PL/SQL code of a warehouse management database application system. The faults were collected from the journal files that contain the documentation of all changes in source files. The result demonstrates that these measures may be useful in predicting the fault concerning with database accesses. In our study, General Regression Neural Network and Ward Neural Network are used to evaluate the capability of this set of SQL metrics in predicting the number of faults in database applications.