Feature selection in an interactive search-based PLA design approach

The Product Line Architecture (PLA) is one of the most important artifacts of a Software Product Line (SPL). PLA design can be formulated as an interactive optimization problem with many conflicting factors. Incorporating Decision Makers’ (DM) preferences during the search process may help the algorithms find more adequate solutions for their profiles. Interactive approaches allow the DM to evaluate solutions, guiding the optimization according to their preferences. However, this brings up human fatigue problems caused by excessive interactions and solutions to evaluate. A common strategy to prevent this problem is limiting the number of interactions and solutions the DM evaluates. Machine Learning (ML) models were also used to learn how to evaluate solutions according to the DM profile and replace them after some interactions. Feature selection performs an essential task as non-relevant and/or redundant features used to train the ML model can reduce the accuracy and comprehensibility of the hypotheses induced by ML algorithms. This study aims to enhance the usage of an ML model in an interactive search-based PLA design approach by addressing two critical challenges: mitigating decision-maker fatigue through feature selection and improving computational efficiency, particularly during testing phases. We applied four selectors, and through results, We managed to reduce 30% of the features and 25% of the time spent on testing, achieving an accuracy of 99%.