A survey on association rule mining for enterprise architecture model discovery

Pinheiro, Carlos; Guerreiro, Sérgio; São Mamede, Henrique

http://hdl.handle.net/10400.2/16058

Use this identifier to reference this record.

Name:	Description:	Size:	Format:
Association Rule Mining_Final.pdf		1.8 MB	Adobe PDF	Download

Send Feedback

Authors

Pinheiro, Carlos

Guerreiro, Sérgio

São Mamede, Henrique

Abstract(s)

Association Rule Mining (ARM) is a field of data mining (DM) that attempts to identify correlations among database items. It has been applied in various domains to discover patterns, provide insight into different topics, and build understandable, descriptive, and predic- tive models. On the one hand, Enterprise Architecture (EA) is a coherent set of principles, methods, and models suit- able for designing organizational structures. It uses view- points derived from EA models to express different concerns about a company and its IT landscape, such as organizational hierarchies, processes, services, applica- tions, and data. EA mining is the use of DM techniques to obtain EA models. This paper presents a literature review to identify the newest and most cited ARM algorithms and techniques suitable for EA mining that focus on automating the creation of EA models from existent data in application systems and services. It systematically identifies and maps fourteen candidate algorithms into four categories useful for EA mining: (i) General Frequent Pattern Mining, (ii) High Utility Pattern Mining, (iii) Parallel Pattern Mining, and (iv) Distribute Pattern Mining. Based on that, it dis- cusses some possibilities and presents an exemplification with a prototype hypothesizing an ARM application for EA mining.

Keywords

Association rule mining Data mining Enterprise architecture mining Enterprise architecture modelling Artificial intelligence

URI

http://hdl.handle.net/10400.2/16058

Citation

Pinheiro, C., Guerreiro, S., & Mamede, H. S. (2023). A Survey on Association Rule Mining for Enterprise Architecture Model Discovery. Business & Information Systems Engineering, 1-22.