Competence Guided Casebase Maintenance for Compositional Adaptation Applications Ditty Mathew and Sutanu Chakraborti Department of Computer Science and Engineering Indian Institute of Technology Madras, Chennai - 600036 {ditty,sutanuc}@cse.iitm.ac.in Abstract. A competence guided casebase maintenance algorithm re- tains a case in the casebase if it is useful to solve many problems and ensures that the casebase is highly competent in the global sense. In this paper, we address the compositional adaptation process (of which single case adaptation is a special case) during casebase maintenance by proposing a case competence model for which we propose a measure called retention score to estimate the retention quality of a case. We also propose a revised algorithm based on the retention score to estimate the competent subset of the casebase. We used regression datasets to test the effectiveness of the competent subset obtained from the proposed model. We also applied this model in a tutoring application and ana- lyzed the competent subset of concepts in tutoring resources. Empirical results show that the proposed model is effective and overcomes the limi- tation of footprint based competence model in compositional adaptation applications. Keywords: Casebase Maintenance, Case Competence, Footprint based Competence model, Compositional Adaptation 1 Introduction Case Based Reasoning(CBR) systems solve new problems by retrieving similar past problems from a casebase and adapting their solutions. The adaptation process can be done in two ways - single case adaptation and compositional adaptation. In single case adaptation, the solution of a single case can be adapted to solve the target problem whereas in compositional adaptation the solutions from multiple cases are combined to produce a new composite solution [16]. Casebase Maintenance is a branch of CBR, which aims at looking into the quality of cases that should be retained in the casebase; the goal is often to maintain a compressed casebase that can solve new problems effectively [12]. We need to ensure that the cases in the compressed casebase would be able to be retrieved and adapted for a wide range of problems in the casebase. Thus, the competence of a casebase can be determined by the ability of the cases in the casebase to solve a large number of problems. A competence guided casebase maintenance algorithm retains a case in the casebase if it is useful to solve many problems and