MCBA: A Matroid Constraint-Based Approach for Composite Service Recommendation Considering Compatibility and Diversity

With the growing popularity of microservices, many companies are encapsulating their business processes as Web APIs for remote invocation. These lightweight Web APIs offer mashup developers an efficient way to achieve complex functionalities without starting from scratch. However, this also presents challenges, such as the concentration of developers'search results on popular APIs limiting diversity, and difficulties in verifying API compatibility. A method is needed to recommend diverse compositions of compatible APIs that fulfill mashup functional requirements from a large pool of candidate APIs. To tackle this issue, this paper introduces a Matroid Constraint-Based Approach (MCBA) for composite service recommendation, consisting of two stages: API composition discovery focusing on compatibility and top-k composition recommendation focusing on diversity. In the first stage, the API composition issue is formulated as a minimal group Steiner tree (MGST) problem, subsequently addressed by a "compression-solution" algorithm. In the second stage, a Maximum Marginal Relevance method under partition matroid constraints (MMR-PMC) is employed to ensure recommendation diversity. Comprehensive experiments on the real-world dataset show that MCBA surpasses several state-of-the-art methods in terms of accuracy, compatibility, diversity, and efficiency.