Overview of Interestingness Measures for Data Mining

In data mining, the primary goal is to discover hidden patterns and knowledge from large datasets. However, not all patterns discovered during the mining process are useful or relevant. To enhance the efficacy of data mining, interestingness measures are developed to evaluate the quality and significance of these patterns. This paper explores the concept of interestingness measures in data mining, categorizes existing approaches, and proposes new metrics for improving the relevance and usefulness of discovered patterns. We also discuss the implications of these measures for real-world applications in various domains, such as business, healthcare, and social sciences.