Maintainability Prediction of Object Oriented Software by using Adaptive Network based Fuzzy System Technique

Today estimating the software size, cost and effort, effectively and accurately is probably the biggest challenge faced by software developers. It has major implications for the management of software development because both the over and under estimations have direct impact for causing damage to software companies. This process of changing the software which has been delivered is called software maintenance. The amount of resource, effort and time required and spent on software maintenance is much more than what is being spent on its development. The relationship between Object Oriented metrics and software maintenance effort is complex and non linear. Therefore, there is considerable research interest in development and application of sophisticated techniques which can be used to construct models for predicting software maintenance effort. The maintenance effort data of two commercial software products is used in the research. The dependent variable in this study is Change. The independent variables are five Object Oriented metrics out of nine proposed metrics on the basis of correlations between different metrics.