Mining affordance-based substitution rules: a dynamic taxonomy approach

Abstract

Association Rule Mining literature has so far focused on generating and pruning positive rules using various metrics of interestingness. However, there are very few studies that explore the mining process of substitution rules. These studies have incorporated limited definition of substitution, either in statistical terms or based on manager's static knowledge. Here we attempt to provide a customer-centric model of substitution rule mining using the lens of affordance. We adopt the approach of a dynamic taxonomy wherein items are positioned based on the affordances they are purchased for. This arrangement contrasts with the traditional static taxonomy approach that highlights manager's static knowledge. We develop an Expected-Actual Substitution Framework to compare relatedness between items in the static and dynamic taxonomies. We also propose the ABS (Affordance Based Substitution) algorithm to mine substitution rules. We come up with a novel interestingness measure to enhance the quality of our substitution rules for effective knowledge discovery. Empirical analyses are performed to show the efficacy of ABS algorithm. This is done with the help of a real-life supermarket dataset. We compare the generated rules with those generated by a classic substitution rule mining algorithm from the literature. Our results show that substitution rules generated through ABS algorithm capture customer perceptions that are generally missed by alternate approaches.