A distance-based approach to find interesting patterns

One of the major problems in knowledge discovery is producing too many trivial and uninteresting patterns. The measurement of interestingness is divided into subjective and objective measures and used to address the problem. In this paper, we propose a novel method to discover interesting patterns by incorporating the domain user's preconceived knowledge. The prior knowledge constitutes a set of hypothesis about the domain. A new parameter called the distance is proposed to measure the gap between the user's existing hypothesis and system-generated knowledge. To evaluate the practicality of our approach, we apply the proposed approach through some real-life data sets and present our findings.