Association Mining from Aggregated Basket

Hirofumi MATSUZAWA  Masayuki NUMAO 

Publication
D - Abstracts of IEICE TRANSACTIONS on Information and Systems (Japanese Edition)  Vol.J95-D  No.2  pp.170-182
Publication Date: 2012/02/01
Online ISSN: 1881-0225
Print ISSN: 1880-4535
Type of Manuscript: Special Section PAPER (Special Section on Data Engineering and Information Management)
Category: 
Keyword: 
association mining,  basket analysis,  frequent pattern,  data generation, 

Full Text(in Japanese): PDF(693.7KB)

Summary: 
Association rule mining is originally developed for the market basket analysis but expected to be used for a wide range of data analysis such as fault analysis in manufacturing. However, in real plant operation, only batch-level fault data is available. Thus, without unit-level data, the straight forward application of basket analysis is difficult. In this paper, we propose a way to extract a frequent fault pattern from the aggregated dataset. We show how to generate a virtual basket from aggregated basket. The fault pattern analysis in a process industry is also shown as a real example.