Classifying Quality of Web Services Using Machine Learning Classification and Cross Validation Techniques

The growing amount of online services provided through the Internet is continually increasing. As a result, consumers are finding it more difficult to choose the proper service among a huge number of functionally comparable candidate services. It is unrealistic to inspect every web service for its quality value since it consumes a lot of resources. As a result, the subject of Web quality of service prediction has gotten a lot of attention in recent years. Using machine learning techniques, the present work suggests a model for the classification of the quality of web services by using cross validation techniques. Four algorithms of classification machine learning are applied in this work: Logistic Regression, Random Forest (DF), Support Vector Machine (SVM) and Neural Network (NN). When comparing the results, it was discovered that the Random Forest had the best accuracy. The cross validation, person correlation and normalization techniques are used in this work to compare them with the result of the algorithms. After choosing the best algorithm, a web service is created for the forecast of quality using Azure Machine Learning studio.