Extended High Utility Pattern Mining: An Answer Set Programming Based Framework and Applications
This work addresses the challenge of flexible pattern mining in data mining, offering a domain-specific tool for tasks like medical prediction, though it appears incremental as it extends existing HUPM concepts.
The paper introduces a new framework for High Utility Pattern Mining (HUPM) using Answer Set Programming (ASP) to specify user-defined utility criteria, enabling analysis from different perspectives, and demonstrates its effectiveness through an application in predicting ICU admission for COVID-19 patients with extensive experimental validation.
Detecting sets of relevant patterns from a given dataset is an important challenge in data mining. The relevance of a pattern, also called utility in the literature, is a subjective measure and can be actually assessed from very different points of view. Rule-based languages like Answer Set Programming (ASP) seem well suited for specifying user-provided criteria to assess pattern utility in a form of constraints; moreover, declarativity of ASP allows for a very easy switch between several criteria in order to analyze the dataset from different points of view. In this paper, we make steps toward extending the notion of High Utility Pattern Mining (HUPM); in particular we introduce a new framework that allows for new classes of utility criteria not considered in the previous literature. We also show how recent extensions of ASP with external functions can support a fast and effective encoding and testing of the new framework. To demonstrate the potential of the proposed framework, we exploit it as a building block for the definition of an innovative method for predicting ICU admission for COVID-19 patients. Finally, an extensive experimental activity demonstrates both from a quantitative and a qualitative point of view the effectiveness of the proposed approach. Under consideration in Theory and Practice of Logic Programming (TPLP)