#### DMCA

## Pruning Derivative Partial Rules During Impact Rule Discovery

### Cached

### Download Links

- [www.csse.monash.edu]
- [www.csse.monash.edu.au]
- [www.csse.monash.edu]
- [www.csse.monash.edu.au]
- DBLP

### Other Repositories/Bibliography

### Citations

3471 |
UCI repository of machine learning databases
- Blake, Merz
- 1998
(Show Context)
Citation Context ...ons We study the effectiveness of the algorithm in table 2 for the derivative partial rule filter by applying it to 10 large databases chosen from KDD archives [4] and UCI machine learning repository =-=[7]-=-, in which many attributes are quantitative. Great differences exist among these databases with the smallest database in size having less than 300 records and the greatest having 2000 times as many re... |

3330 | A.: Mining association rules between sets of items in large databases
- Agrawal, Imieliński, et al.
- 1993
(Show Context)
Citation Context ...patterns and regularities that satisfy some user-defined set of constraints in a population, with respect to a set of available sample data. The best known such approach is association rule discovery =-=[1]-=-. Most approaches seeks rules A → C for which there is a correlation between the antecedent A and the consequent C. However, whenever one such rule is found, there is a risk that many derivative and p... |

634 | R.: Beyond market baskets: Generalizing association rules to dependence rules
- Silverstein, Brin, et al.
- 1998
(Show Context)
Citation Context ...scretized quantitative attributes in distributional-consequent rules are described with their distributions. Association rule discovery [1], contrast sets discovery [5] and correlation rule discovery =-=[8]-=- are examples of propositional exploratory rule discovery, while impact rule [14] or quantitative association rule discovery [2], as is variously known, belongs to the class of distributional-conseque... |

242 | Generating Non-Redundant association rule
- Zaki
- 2000
(Show Context)
Citation Context ...ated to either A or C, AB will also turn out to be correlated with C. Considerable research has been devoted to automatically identify and discard such derivative rules. The closed itemset techniques =-=[12, 3, 16]-=- can identify rulessfor which some elements can be removed without changing the support of the rule. Minimum improvement techniques [6] can to identify rules for which some elements can be removed wit... |

172 |
The UCI KDD archive. http://kdd.ics.uci.edu
- Hettich, Bay
- 1999
(Show Context)
Citation Context ...d to be removed. 5 Experimental Evaluations We study the effectiveness of the algorithm in table 2 for the derivative partial rule filter by applying it to 10 large databases chosen from KDD archives =-=[4]-=- and UCI machine learning repository [7], in which many attributes are quantitative. Great differences exist among these databases with the smallest database in size having less than 300 records and t... |

153 | Pruning and Summarizing the Discovered Associations.
- Liu, Hsu, et al.
- 1999
(Show Context)
Citation Context ...so applied to assess whether there is evidence that no elements can be removed without significantly altering the status of the rule with respect to the population from which the sample data is drawn =-=[11, 5, 9]-=-. However, all these techniques relate only to identifying rules that are derivative due to the addition of irrelevant or unproductive elements. There exists, however, another type of derivative rules... |

109 | Detecting Group Differences: Mining Contrast Sets,”
- Bay, Pazzani
- 2001
(Show Context)
Citation Context ...so applied to assess whether there is evidence that no elements can be removed without significantly altering the status of the rule with respect to the population from which the sample data is drawn =-=[11, 5, 9]-=-. However, all these techniques relate only to identifying rules that are derivative due to the addition of irrelevant or unproductive elements. There exists, however, another type of derivative rules... |

106 | A statistical theory for quantitative association rules.
- Aumann, Lindell
- 2003
(Show Context)
Citation Context ...scovery [1], contrast sets discovery [5] and correlation rule discovery [8] are examples of propositional exploratory rule discovery, while impact rule [14] or quantitative association rule discovery =-=[2]-=-, as is variously known, belongs to the class of distributional-consequent rule discovery. It is argued that distributional-consequent rules are able to provide better descriptions of the interrelatio... |

90 | OPUS: An efficient admissible algorithm for unordered search
- Webb
- 1995
(Show Context)
Citation Context ... records in the database. Coverage(A) is the number of records covered by A. coverage(A) = |coverset(A)|.s3 Impact Rule Discovery We construct our impact rule discovery algorithm on the basis of OPUS =-=[13]-=- search algorithm, which enables successful discovery of the top k impact rules that satisfy a certain set of user-specified constraints. We characterized the terminology of k-optimal impact rule disc... |

39 | Discovering associations with numeric variables .In:
- Webb
- 2001
(Show Context)
Citation Context ... variable, referred to as the target and is described using its distribution. This paper investigates the identification of the second type of derivative rules in the context of impact rule discovery =-=[9, 14]-=-. The rest of this paper is organized like this: a brief introduction to exploratory rule discovery related concepts is presented in section 2. The definitions and notations of impact rule discovery i... |

7 |
Rafik Taouil, Gerd Stumme, and Lotfi Lakhal. Mining minimal non-redundant association rules using frequent closed itemsets
- Bastide, Pasquier
- 2000
(Show Context)
Citation Context ...ated to either A or C, AB will also turn out to be correlated with C. Considerable research has been devoted to automatically identify and discard such derivative rules. The closed itemset techniques =-=[12, 3, 16]-=- can identify rulessfor which some elements can be removed without changing the support of the rule. Minimum improvement techniques [6] can to identify rules for which some elements can be removed wit... |

7 |
Rakesh Agrawal, and Dimitrios Gunopulos. Constraint-based rule mining in large, dense databases
- Bayardo
(Show Context)
Citation Context ...ard such derivative rules. The closed itemset techniques [12, 3, 16] can identify rulessfor which some elements can be removed without changing the support of the rule. Minimum improvement techniques =-=[6]-=- can to identify rules for which some elements can be removed without decreasing rule confidence. However, since exploratory rule discovery seeks to discover rules characterizing the features in a pop... |

7 | Discarding insignificant rules during impact rule discovery in large databases
- Huang, Webb
- 2005
(Show Context)
Citation Context ...so applied to assess whether there is evidence that no elements can be removed without significantly altering the status of the rule with respect to the population from which the sample data is drawn =-=[11, 5, 9]-=-. However, all these techniques relate only to identifying rules that are derivative due to the addition of irrelevant or unproductive elements. There exists, however, another type of derivative rules... |

4 | Statistically sound exploratory rule discovery
- Webb
- 2004
(Show Context)
Citation Context ...model from the available data that is expected to maximize some objective function of interestingness on unknown future data. Predictions or classifications are done on the basis of this single model =-=[15]-=-. However, alternative models may exist that perform equally well. Thus, it is not always sensible to choose only one of the“best” models. Moreover the criteria for deciding whether a model is best or... |

3 |
Rafik Taouil, and Lotfi Lakhal. Closed set based discovery of small covers for association rules
- Pasquier, Bastide
- 1999
(Show Context)
Citation Context ...ated to either A or C, AB will also turn out to be correlated with C. Considerable research has been devoted to automatically identify and discard such derivative rules. The closed itemset techniques =-=[12, 3, 16]-=- can identify rulessfor which some elements can be removed without changing the support of the rule. Minimum improvement techniques [6] can to identify rules for which some elements can be removed wit... |

1 | Efficiently identification of exploratory rules’ significance - Huang, Webb - 2004 |