An Empirical Analysis on the Prediction of Web Service Anti-patterns Using Source Code Metrics and Ensemble Techniques

Today's software program enterprise uses web services to construct distributed software systems based on the Service Oriented Architecture (SOA) paradigm. The web service description is posted by a web service provider, which may be observed and invoked by a distributed application. Service-Based Systems (SBS) need to conform themselves through years to fit within the new user necessities. These may result in the deterioration of the quality and design of the software systems and might reason the materialization of insufficient solutions called Anti-patterns. Anti-pattern detection using object-oriented source code metrics may be used as part of the software program improvement life cycle to lessen the maintenance of the software system and enhance the quality of the software. The work is motivated by developing an automatic predictive model for predicting web services anti-patterns using static evaluations of the source code metrics. The center ideology of this work is to empirically investigate the effectiveness of different variants of data sampling technique, Synthetic Minority Over Sampling TEchnique (SMOTE), and the ensemble learning techniques in the prediction of web service anti-patterns.