Abstract: An approach to developing software for business applications is known as service-oriented architecture (SOA). This paper discusses the essential aspects of developing a framework for evaluating SOA's maintainability. The SOA is maintained by the framework using a cyclomatic complexity of various methods and a fuzzy model. 15,714 Java files and 1.4 million lines are implemented in this framework. In order to determine whether or not the inputs and outputs are maintainable, the 10886 dataset is used. The maintainability of 276 projects is being evaluated. The majority of the files in the study projects are thought to be simple to maintain. The goal of this framework is to report on and improve the working relationship and strategies that exist between the development department and the client support department. This framework should be followed for each complaint or demand for change from customers. The functionalities of the proposed framework include the following: receiving and logging client calls; focusing on and classifying issues; assigning issues to client support, engineers, and coders; allowing for issue fixes and minor improvements; assessing, classifying, and completing issues; identifying normal repeating issues and closing them for all clients; measuring and further developing client assistance by giving; and handling requests. Lower cyclomatic complexity helps programs comprehend and is less risky to modify. The mean relative error of various codes is calculated and compared in this paper using cyclomatic complexity and a fuzzy model. It is concluded that SOA maintenance is simple if the MARE is less than 0.269406586.

Key words: neural network (NN), service-oriented architecture (SOA), artificial neural network (ANN)