Incremental Footprint-Based Retrieval

Case-based reasoning systems solve new problems by retrieving and adapting problem solving experiences stored as cases in a case-base. Success depends largely on the performance of the case retrieval algorithm used. Smyth & McKenna [15] have described a novel retrieval technique, called footprint-based retrieval, which is guided by a model of case competence. Footprint-based retrieval as it stands benefits from superior efficiency characteristics and achieves near-optimal competence and quality characteristics. In this paper we describe a simple but important extension to footprint-based retrieval. Empirically we show that this new algorithm can deliver optimal retrieval performance while at the same time retaining the efficiency benefits of the original footprint-based retrieval method.