Onotology-based service discovery for intelligent Big Data analytics

Organizations utilizing advanced analytics techniques to gain real value from Big Data will grow faster than their competitors and seize new opportunities. Cross-Industry Standard Process for Data Mining (CRISP-DM) is an industry-proven way to build predictive analytics models across the enterprise. However, the manual process in CRISP-DM hinders faster decision making on real-time application for efficient data analysis. Thus, in our previous work, we presented an approach to automate the CRISP-DM process using Automatic Service Composition (ASC). Further, we proposed an ontology-based workflow generation method to automate by considering the planning stage. In this paper, we focus on discovery stage of the ASC. Here, we apply ontology based discovery method to identify candidate services for abstract tasks in workflow. We compute the degree of semantic matching for a given pair of abstract task and web service instance by applying different filters. Further, we consider clustering based discovery based method to increase the efficiency of the discovery. Experimental results show that our discovery approach works efficiently.