Affiliations: [a] Department of Computer Science, University of Calgary, Calgary, AB, Canada | [b] School of Computer Science, The Queen's University of Belfast, Belfast, UK
Correspondence:
[*]
Corresponding author: Shang Gao, Department of Computer Science, University of Calgary 2500 University Dr. NW Calgary, Alberta Canada T2N 1N4. Tel.: +1 403 220 6015; Fax: +1 403 284 4707; E-mail: [email protected].
Abstract: Mining sequential patterns is an important activity in computerized data analysis, and further analysis of discovered patterns can lead to more important findings in a post mining stage. Methods that integrate the traditional mining tasks with a knowledge representation facilitating such as post pruning are therefore needed. In this paper a set-based approach to mining frequent sequential patterns in customer transactional databases is described which includes an extensible knowledge representation. This knowledge representation is a byproduct of the set-based approach which contributes to facilitate post data mining and analysis. The proposed approach employs a set based knowledge representation and improves the performance of Apriori based algorithms while preserving a complete set of sequential patterns. It takes advantage of an incremental mining methodology and provides a rich knowledge representation. Performance results of the proposed approach are compared to the performance of existing sequential pattern mining algorithms including GSP (Generalized Sequential Pattern) and PrefixSpan. The effective knowledge representation inferred from the set based approach can be extended to other data mining tasks and data analysis models. Such extension is demonstrated by two instances of enriched knowledge representations in sequential databases, namely Set Occurrence Tables and Set Distance computations, along with their use of association rules generation, feature selection and ad hoc analysis in the post mining stage.
Keywords: Data mining, sequential patterns, set computation, knowledge representation, incremental mining
