@comment{{Bibliography by Michael Hahsler (http://wwwai.wu-wien.ac.at/~hahsler)}}
@comment{{This file has been generated by bib2bib 1.95}}
@comment{{Command line: /usr/bin/bib2bib -c 'category : "var-support\|no-support"' -ob tmp.bib association_rules_url.bib}}
@article{arules:Ahmed:2000,
author = {Khalil M. Ahmed and Nagwa M. El-Makky and Yousry Taha},
title = {A note on ''{B}eyond market baskets: {G}eneralizing association rules to correlations''},
journal = {SIGKDD Explorations},
year = {2000},
volume = {1},
pages = {46--48},
number = {2},
abstract = {A reply to Brin et al. (1997). The authors state that the chi-square
test tests the whole contingency table, but for larger than 2x2 tables
we want to test dependence for single cells.},
category = {no-support},
publisher = {ACM Press},
google = {http://www.google.com/search?q=%22A+note+on+''Beyond+market+baskets:+Generalizing+association+rules+to+correlations''%22},
googlescholar = {http://scholar.google.com/scholar?q=%22A+note+on+''Beyond+market+baskets:+Generalizing+association+rules+to+correlations''%22}
}
@inproceedings{arules:Brin:1997b,
author = {Sergey Brin and Rajeev Motwani and Craig Silverstein},
title = {Beyond Market Baskets: Generalizing Association Rules to Correlations},
booktitle = {SIGMOD 1997, Proceedings ACM SIGMOD International Conference on Management
of Data},
year = {1997},
pages = {265--276},
address = {Tucson, Arizona, USA},
month = {May},
abstract = {Proposes to use the chi-square test for correlation. For an itemset
of length l, the test is carried out on a l-dimensional contingency
tables. A problem is cells with low counts and multiple tests.},
category = {no-support},
google = {http://www.google.com/search?q=%22Beyond+Market+Baskets:+Generalizing+Association+Rules+to+Correlations%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Beyond+Market+Baskets:+Generalizing+Association+Rules+to+Correlations%22}
}
@article{arules:Cohen:2001,
author = {Edith Cohen and Mayur Datar and Shinji Fujiwara and Aristides Gionis
and Piotr Indyk and Rajeev Motwani and Jeffrey D. Ullman and Cheng
Yang},
title = {Finding Interesting Associations without Support Pruning},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2001},
volume = {13},
pages = {64--78},
number = {1},
abstract = {Uses similarity measures between hashed values of rows in a transaction
database. The approach in the paper was only shown for associations
between two items.},
category = {no-support},
google = {http://www.google.com/search?q=%22Finding+Interesting+Associations+without+Support+Pruning%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Finding+Interesting+Associations+without+Support+Pruning%22}
}
@inproceedings{arules:DuMouchel:2001,
author = {William DuMouchel and Daryl Pregibon},
title = {Empirical {B}ayes Screening for Multi-Item Associations},
booktitle = {Proceedings of the ACM SIGKDD Intentional Conference on Knowledge
Discovery in Databases and Data Mining (KDD-01)},
year = {2001},
editor = {F. Provost and R. Srikant},
pages = {67--76},
publisher = {ACM Press},
abstract = {Search for unusually frequent itemsets using statistical methods.
First, the authors propose stratification of the data to avoid finding
spurious associations within strata. Then the deviation of the observed
frequency over a baseline frequency (based on independence) is used.
Since the deviation is unreliable for low counts, an empirical Bayes
model (its 95\% confidence limit) is used to produce a posterior
distribution of the true ratio of actual to baseline frequencies.
The Bayes model gives ratios close to the observed ratios for large
samples and reduces (shrinks) the ratio if the sample size gets small
(to smooth away noise). For multi-item associations log-linear models
are proposed to find higher order associations which cannot be explained
by pairwise associations. },
category = {no-support,theory},
google = {http://www.google.com/search?q=%22Empirical+Bayes+Screening+for+Multi-Item+Associations%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Empirical+Bayes+Screening+for+Multi-Item+Associations%22}
}
@article{arules:Hahsler:2006,
author = {Michael Hahsler},
title = {A Model-Based Frequency Constraint for Mining Associations from Transaction Data},
journal = {Data Mining and Knowledge Discovery},
year = {2006},
volume = {13},
pages = {137--166},
number = {2},
month = {September},
abstract = {Develops a novel model-based frequency constraint as an alternative
to a single, user-specified minimum support. The constraint utilizes
knowledge of the process generating transaction data by applying
a simple stochastic mixture model (the NB model) and uses a user-specified
precision threshold to find local frequency thresholds for groups
of itemsets (NB-frequent itemsets). The new constraint provides improvements
over a single minimum support threshold and that the precision threshold
is more robust and easier to set and interpret by the user. },
category = {no-support},
doi = {10.1007/s10618-005-0026-2},
issn = {1384-5810},
google = {http://www.google.com/search?q=%22A+Model-Based+Frequency+Constraint+for+Mining+Associations+from+Transaction+Data%22},
googlescholar = {http://scholar.google.com/scholar?q=%22A+Model-Based+Frequency+Constraint+for+Mining+Associations+from+Transaction+Data%22}
}
@inproceedings{arules:Li:1999,
author = {Jinyan Li and Xiuzhen Zhang and Guozho Dong and Kotagiri Ramamohanarao
and Qun Sun},
title = {Efficient Mining of High Confidence Association Rules without Support Thresholds},
booktitle = {Principles of Data Mining and Knowledge Discovery PKDD'99, LNAI 1704,
Prague, Czech Republic},
year = {1999},
editor = {J. Zytkow and J. Rauch},
pages = {406--411},
publisher = {Springer-Verlag},
abstract = {This paper used JUMPING EMERGING PATTERNS to mine a border for top
rules (rules with 100\% confidence) for a given consequent. The drawbacks
are that only one consequent is mined at a time and that finding
rules with other than 100\% confidence is difficult.},
category = {no-support},
google = {http://www.google.com/search?q=%22Efficient+Mining+of+High+Confidence+Association+Rules+without+Support+Thresholds%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Efficient+Mining+of+High+Confidence+Association+Rules+without+Support+Thresholds%22}
}
@inproceedings{arules:Liu:1999,
author = {Bing Liu and Wynne Hsu and Yiming Ma},
title = {Mining Association Rules with Multiple Minimum Supports},
booktitle = {Proceedings of the fifth ACM SIGKDD international conference on Knowledge
discovery and data mining (KDD-99)},
year = {1999},
pages = {337--341},
publisher = {ACM Press},
abstract = {Adapts APRIORI to work with different minimum support thresholds assigned
to different items (minimum item supports, MIS). To preserve the
downward closure property of support item sorting using the MIS values
is used.},
category = {var-support},
google = {http://www.google.com/search?q=%22Mining+Association+Rules+with+Multiple+Minimum+Supports%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Mining+Association+Rules+with+Multiple+Minimum+Supports%22}
}
@article{arules:Omiecinski:2003,
author = {Edward R. Omiecinski},
title = {Alternative Interest Measures for Mining Associations in Databases},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2003},
volume = {15},
pages = {57--69},
number = {1},
month = {Jan/Feb},
abstract = {Omiecinski introduced several alternatives to support. The first measure,
ANY-CONFIDENCE, is defined as the confidence of the rule with the
largest confidence which can be generated from an itemset. The author
states that although finding all itemsets with a set any-confidence
would enable us to find all rules with a given minimum confidence,
any-confidence cannot be used efficiently as a measure of interestingness
since confidence is not downward closed. The second introduced measure
is ALL-CONFIDENCE. This measure is defined as the smallest confidence
of all rules which can be produced from an itemset, i.e., all rules
produced form an itemset will have a confidence greater or equal
to its all-confidence value. BOND, the last measure, is defined as
the ratio of the number of transactions which contain all items of
an itemset to the number of transactions which contain at least one
of these items. Omiecinski showed that bond and all-confidence are
downward closed and, therefore, can be used for efficient mining
algorithms. },
category = {no-support},
google = {http://www.google.com/search?q=%22Alternative+Interest+Measures+for+Mining+Associations+in+Databases%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Alternative+Interest+Measures+for+Mining+Associations+in+Databases%22}
}
@inproceedings{arules:Seno:2001,
author = {Masakazu Seno and George Karypis},
title = {LPMiner: An Algorithm for Finding Frequent Itemsets Using Length Decreasing Support Constraint},
booktitle = {Proceedings of the 2001 IEEE International Conference on Data Mining,
29 November -- 2 December 2001, San Jose, California, USA},
year = {2001},
editor = {Nick Cercone and Tsau Young Lin and Xindong Wu},
pages = {505--512},
publisher = {IEEE Computer Society},
abstract = {To find longer frequent itemsets, the minimal support requirement
decreases as a function of the itemset length. A algorithm based
on the FP-tree is presented and a property called small valid extension
(SVE) is introduced which makes mining efficient in absence of downward
closure.},
category = {var-support},
google = {http://www.google.com/search?q=%22LPMiner:+An+Algorithm+for+Finding+Frequent+Itemsets+Using+Length+Decreasing+Support+Constraint%22},
googlescholar = {http://scholar.google.com/scholar?q=%22LPMiner:+An+Algorithm+for+Finding+Frequent+Itemsets+Using+Length+Decreasing+Support+Constraint%22}
}
@article{arules:Seno:2005,
author = {Masakazu Seno and George Karypis},
title = {Finding Frequent Itemsets Using Length-Decreasing Support Constraint},
journal = {Data Mining and Knowledge Discovery},
year = {2005},
volume = {10},
pages = {197--228},
abstract = {See Seno and Karypis 2001.},
category = {var-support},
google = {http://www.google.com/search?q=%22Finding+Frequent+Itemsets+Using+Length-Decreasing+Support+Constraint%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Finding+Frequent+Itemsets+Using+Length-Decreasing+Support+Constraint%22}
}
@article{arules:Silverstein:1998,
author = {Craig Silverstein and Sergey Brin and Rajeev Motwani},
title = {Beyond Market Baskets: Generalizing Association Rules to Dependence Rules},
journal = {Data Mining and Knowledge Discovery},
year = {1998},
volume = {2},
pages = {39--68},
abstract = {Journal version of Brin et al. (1997). },
category = {no-support},
google = {http://www.google.com/search?q=%22Beyond+Market+Baskets:+Generalizing+Association+Rules+to+Dependence+Rules%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Beyond+Market+Baskets:+Generalizing+Association+Rules+to+Dependence+Rules%22}
}
@inproceedings{arules:Tao:2003,
author = {Feng Tao and Fionn Murtagh and Mohsen Farid},
title = {Weighted Association Rule Mining using Weighted Support and Significance Framework},
booktitle = {Proceedings of The Ninth ACM SIGKDD International Conference on Knowledge
Discovery and Data Mining (KDD-2003)},
year = {2003},
address = {Washington, DC},
publisher = {ACM Press},
abstract = {Uses attributes of the items (e.g., price, page dwelling time) to
WEIGHT SUPPORT. A support and significance framework is presented
which possesses a weighted downward closure property important for
pruning the search space.},
category = {var-support},
google = {http://www.google.com/search?q=%22Weighted+Association+Rule+Mining+using+Weighted+Support+and+Significance+Framework%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Weighted+Association+Rule+Mining+using+Weighted+Support+and+Significance+Framework%22}
}
@inproceedings{arules:Wang:2001,
author = {Ke Wang and Yu He and David W. Cheung},
title = {Mining confident rules without support requirement},
booktitle = {Proceedings of the tenth international conference on Information
and knowledge management},
year = {2001},
pages = {89 - 96},
address = {New York, NY},
publisher = {ACM Press},
abstract = {The paper shows that for data with categorical attributes a UNIVERSAL-EXISTENTIAL
UPWARD CLOSURE exists for confidence. With this property algorithms
with confidence-based pruning are possible that use a level-wise
(from k to k-1) candidate generation are. The paper also discusses
a disk-based implementation.},
category = {no-support},
google = {http://www.google.com/search?q=%22Mining+confident+rules+without+support+requirement%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Mining+confident+rules+without+support+requirement%22}
}
@inproceedings{arules:Xiong:2003,
author = {Hui Xiong and Pang-Ning Tan and Vipin Kumar},
title = {Mining Strong Affinity Association Patterns in Data Sets with Skewed Support Distribution},
booktitle = {Proceedings of the IEEE International Conference on Data Mining,
November 19--22, 2003, Melbourne, Florida},
year = {2003},
editor = {Bart Goethals and Mohammed J. Zaki},
pages = {387--394},
month = {November},
abstract = {Support-based pruning strategies are not effective for data sets with
skewed support distributions. The authors propose the concept of
hyperclique pattern, which uses an objective measure called h-confidence
(equal to all-confidence by Omiecinski, 2003) to identify strong
affinity patterns. The generation of so-called cross-support patterns
(patterns with items with substantially different support) is avoided
by h-confidence's cross-support property. },
category = {no-support},
google = {http://www.google.com/search?q=%22Mining+Strong+Affinity+Association+Patterns+in+Data+Sets+with+Skewed+Support+Distribution%22},
googlescholar = {http://scholar.google.com/scholar?q=%22Mining+Strong+Affinity+Association+Patterns+in+Data+Sets+with+Skewed+Support+Distribution%22}
}
This file was generated by bibtex2html 1.95.