A domain-centric approach for recommending architectural tactics to satisfy quality concerns

Architectural tactics such as heartbeat, resource pooling, and scheduling, offer proven solutions for systematically increasing the reliability, security, performance, and other critical characteristics of a software system. Current literature on architectural tactics advocates a requirements-driven approach for deciding when and where tactics should be used in order to address specific quality concerns. In this paper we explore a domain-driven approach by building predictor models which capture relationships between topical domain concepts and the use of specific architectural tactics. Based on an extensive analysis of over 1000 open source systems, we identify significant correlations between domain topics and architectural tactics, and use this information to construct a predictor for generating tactic-related recommendations. Our approach is validated through a series of experiments which demonstrate the ability to generate package level recommendations. It is also illustrated through a worked example of package-level recommendations in the OfBiz Neogia system.