On the Discovery of Frequent Gradual Patterns: A Symbolic AI-Based Framework

Gradual patterns extract useful knowledge from numerical databases as attribute co-variations. This article introduces a constraint-based modeling framework for the problem of extracting frequent gradual patterns from numerical data. Our declarative framework provides a principle way to take advantage of recent advancements in satisfiability testing and several features of modern SAT solvers to enumerating gradual patterns from input data. Interestingly, our approach can easily be extended to accommodate additional requirements, including temporal constraints, enabling the extraction of more specific patterns across a wide spectrum of gradual pattern mining applications. An empirical evaluation conducted on two real-world datasets demonstrates the efficacy of the proposed approach.