Personalized web service recommendation through mishmash technique and deep learning model

Abstract

Discovering the relevant web services for specific applications in the dynamically changing business world becomes very critical. Researchers have used many ontology based approaches to address the heterogeneity prevailing in many business problems. Our work focuses on Mishmash technique with rich semantics representation focusing on word segmentation and segregation to reduce load on the server side. We also propose a tokenized, stemmed feature weighted RDF data producing SPARQL result set for generating relevant web services. A deep learning model to learn the retrieved web services using adaptive learning approach was also used, so that a composition of relevant service domain is framed for reducing the time taken for future queries. The model classifier is dynamically built based on the new information’s at every iteration, and once an acceptable range defined is achieved, the training accuracy is calculated. The trial results show that the relevant web services are grouped together by the weights in the deep learning model with a training accuracy of 94% by the Mishmash method when compared to Hyperclique method. The testing accuracy of Mishmash method was found to be 95.5% when compared to Hyperclique, which was found to be 92%. Thus the proposed Mishmash method along with Deep learning model can be used as a dynamic decision making model in the Service oriented architecture space.