Diversified and compatible web APIs recommendation based on game theory in IoT

With the ever-increasing popularity of Internet of Things (IoT), massive enterprises are attempting to encapsulate their developed outcomes into various lightweight Web Application Programming Interfaces (APIs) that can be accessible remotely. In this context, finding and writing a list of existing Web APIs that can collectively meet the functional needs of software developers has become a promising approach to economically and easily develop successful mobile applications. However, the number and diversity of candidate IoT Web APIs places an additional burden on application developers’ Web API selection decisions, as it is often a challenging task to simultaneously ensure the diversity and compatibility of the final set of Web APIs selected. Considering this challenge and latest successful applications of game theory in IoT, a Diversified and Compatible Web APIs Recommendation approach, namely DivCAR, is put forward in this paper. First of all, to achieve API diversity, DivCAR employs random walk sampling technique on a pre-built “API-API” correlation graph to generate diverse “API-API” correlation subgraphs. Afterwards, with the diverse “API-API” correlation subgraphs, the compatible Web APIs recommendation problem is modeled as a minimum group Steiner tree search problem. A sorted set of multiple compatible and diverse Web APIs are returned to the application developer by solving the minimum group Steiner tree search problem. At last, a set of experiments are designed and implemented on a real dataset crawled from www.programmableweb.com. Experimental results validate the effectiveness and efficiency of our proposed DivCAR approach in balancing the Web APIs recommendation diversity and compatibility.