Regularizing Matrix Factorization with Implicit User Preference Embeddings for Web API Recommendation

Mashups have emerged as a popular technique, which composes value-added web services/APIs, to realize some complicated business needs. The rapid increase in the number of similarly functional web APIs, makes it challenging to find relevant ones for mashup development. Recommender systems have become highly important, because they reduce the myriad of web APIs, during web API selection. Most existing web API recommender systems, however, neglect the implicit user preferences, to personalize and precisely recommend web APIs to mashup developers. It is for this reason, that this work proposes a method, which considers both explicit and implicit user personalized preferences to make personalized web API recommendations, while improving recommendation accuracy and diversity. Specifically, we propose a regularized user preference embedded matrix factorization method, to personalize recommendations. We take advantage of users' implicit personalized preferences, which are obtained from their interactions (i.e. invoking or following) with web APIs and other users in the system. We demonstrate the effectiveness of our method by conducting extensive experiments on a real-world dataset crawled from www.programmableweb.com. We also compare our method with some baseline recommendation methods for verification.