Opportunity Cost Estimation Using Clustering and Association Rule Mining

Abstract

Information mining strategies are most appropriate for the classification, useful patterns extraction and predications which are imperative for business support and decision making. However, an efficient method for evaluating the penalty cost has not been proposed. In this article, considering the cross-selling effect, a quantitative approach to estimate the opportunity cost based on association rules in each cluster is proposed. This article helps in better decision making for improving sales, services and quality, which is useful mechanism for business support, investment, and surveillance. A numerical illustration is utilized to clarify the new approach. Further, to understand the effect of above approach in the real scenario, experiments are conducted on a real-world dataset.