Download: PDF.
“Attribute Constrained Rules For Partially Labeled Sequence Completion” by Chad A. Williams, Peter C. Nelson, and Abolfazl Mohammadian. Advances in Data Mining - Applications and Theoretical Aspects, vol. 5633, July 2009, pp. 338 - 352.
Sequential pattern and rule mining have been the focus of much research in the data mining community, however predicting missing sets of elements within a sequence remains a challenge. Recent work in survey design suggests that if these missing elements can be inferred with a higher degree of certainty, it would greatly reduce the time burden on survey participants. To address this problem and the more general problem of missing sensor data, we introduce a new form of constrained sequential rules that use attribute presence to better capture rule confidence in sequences with missing data than previous constraint based techniques. Specifically we examine the problem of given a partially labeled sequence of sets of attributes, how well can the missing attributes be inferred. Our study shows this technique significantly improves prediction robustness when even large amounts of sequence data are missing compared to traditional techniques, as demonstrated on a publicly available travel survey data set.
Keywords: Classification, prediction,association rules, pattern mining, sequential rules,attribute constrained rules
Download: PDF.
BibTeX entry:
@article{WNM09,
author = {Chad A. Williams and Peter C. Nelson and Abolfazl Mohammadian},
title = {Attribute Constrained Rules For Partially Labeled Sequence
Completion},
journal = {Advances in Data Mining - Applications and Theoretical Aspects},
volume = {5633},
pages = {338 - 352},
address = {Leipzig, Germany},
month = jul,
year = {2009},
url = {http://www.springerlink.com/content/h7726636q533q36k}
}