## On Characterization and Discovery of Minimal Unexpected Patterns in Data Mining Applications

Citations: | 9 - 0 self |

### BibTeX

@MISC{Padmanabhan_oncharacterization,

author = {Balaji Padmanabhan and Alexander Tuzhilin},

title = {On Characterization and Discovery of Minimal Unexpected Patterns in Data Mining Applications},

year = {}

}

### OpenURL

### Abstract

A drawback of traditional data mining methods is that they do not leverage prior knowledge of users. In many business settings, managers and analysts have significant intuition based on several years of experience. In prior work we proposed a method that could discover unexpected patterns in data by using this domain knowledge in a systematic manner. In this paper we continue our focus on discovering unexpected patterns and propose new methods for discovering a minimal set of unexpected patterns that discover orders of magnitude fewer patterns and yet retain most of the truly unexpected ones. We demonstrate the strengths of this approach experimentally using a case study application in a marketing domain.

### Citations

2606 | Mining association rules between sets of items in large databases
- AGRAWAL, IMIELINSKY, et al.
- 1993
(Show Context)
Citation Context ...dge about the domain and use these beliefs to seed the search for all unexpected patterns defined as rules. In particular, let I = {i1, i2, …, im} be a set of discrete attributes (also called “ite=-=ms” [AIS93]),-=- some of them being ordered and others unordered. Let D = {T1, T2, ..., TN} be a relation consisting on N transactions [AMS+95] T1, T2, ..., TN over the relation schema {i1, i2, …, im}. Also, let an... |

704 | From data mining to knowledge discovery: an overview, p. 1–34 - Fayyad, Piatetsky-Shapiro, et al. - 1996 |

584 |
Generalization as search
- Mitchell
- 1982
(Show Context)
Citation Context ...scovery of unexpected patterns, we will focus only on minimality as related to this problem. One of the early influential works related to minimality of a set of patterns was presented by Mitchell in =-=[M82]-=-. In particular, [M82] presents a unifying approach to the problem of generalizing knowledge (that, for example, can be represented as rules) by viewing generalization as a search problem. Moreover, b... |

504 | Fast discovery of association rules - Agrawal, Mannila, et al. - 1996 |

481 | A note on inductive generalization - Plotkin - 1969 |

368 | Mining quantitative association rules in large relational tables
- Agrawal, Srikant
- 1996
(Show Context)
Citation Context ...nd applicable to more general classes of rules. Moreover, [TKR+95] focuses on pruning already discovered rules and does not address the issue of direct discovery of minimal sets. Finally, the work of =-=[SA96]-=- and [BAG99] is also related to the problem of discovering minimal sets of rules. In particular, [SA96] and [BAG99] provide methods for eliminating rules such that the support and/or confidence values... |

325 | Learning structural descriptions from examples - Winston - 1975 |

246 | Mining Association Rules with Item Constraints - Agrawal, Srikant, et al. - 1997 |

230 | What makes patterns interesting in knowledge discovery systems
- Silberschatz, Tuzhilin
- 1996
(Show Context)
Citation Context ... of the term "most unexpected". In subsequent work, we will study the issue of generating the "most unexpected patterns" by characterizing the degree of unexpectedness for patterns=-= along the lines of [ST96]. In-=- the context of objective measures of interestingness, [BA99] discuss interesting approaches to finding the “most interesting” patterns. Given the relative advantages of the two methods to discove... |

213 | Finding interesting rules from large sets of discovered association rules. CIKM-94 - Klemetinen, Mannila, et al. - 1994 |

157 | Constraint-based rule mining in large, dense databases. Data Mining and Knowledge Discovery
- Bayardo, Agrawal, et al.
- 2000
(Show Context)
Citation Context ...le to more general classes of rules. Moreover, [TKR+95] focuses on pruning already discovered rules and does not address the issue of direct discovery of minimal sets. Finally, the work of [SA96] and =-=[BAG99]-=- is also related to the problem of discovering minimal sets of rules. In particular, [SA96] and [BAG99] provide methods for eliminating rules such that the support and/or confidence values of these ru... |

153 | On subjective measures of interestingness in knowledge discovery
- Silberschatz, Tuzhilin
- 1995
(Show Context)
Citation Context ...main algorithm, ZoomUR (presented in the next section), with Apriori not in terms of itemsets but directly in terms of the number of rules generated. A key strength of MinZoominUR, compared to ZoomUR =-=[PT99]-=- and Apriori [AMS+95], is that rule discovery is integrated into the itemset generation procedure and hence it can greatly reduce the number of itemsets generated in subsequent iterations - as [AMS+95... |

135 | Mining the most interesting rules
- Bayardo, Agrawal
- 1999
(Show Context)
Citation Context ...an the one proposed in [M82]. To address these limitations, [BA99, LHM99, SLR+99, TKR+95, SA96, BAG99] provide alternate approaches to characterizing a minimal set of discovered rules. In particular, =-=[BA99] pre-=-sents an approach that finds the 5s“most interesting rules”, defined as rules that lie on a support and confidence frontier. Further [BA99] proves that these rules necessarily contain the stronges... |

132 | Version spaces: a candidate elimination approach to rule learning - Mitchell - 1977 |

104 | The interestingness of deviations - Piatetsky-Shapiro, Matheus - 1994 |

104 | A belief-driven method for discovering unexpected patterns
- Padmanabhan, Tuzhilin
- 1998
(Show Context)
Citation Context ...ion value3 ≤ attribute ≤ value4 belongs to CONTR(head) if the ranges [value1, value2] and [value3, value4] do 5 The inputs to algorithms presented in this section are the same as the inputs to Zoo=-=mUR [PT98] d-=-escribed in Section 2. 13snot overlap. (2) If the head of the belief is of the form attribute = val (attribute is unordered), then condition attribute = vp belongs to CONTR(head) if vp ∈ { v1, v2,..... |

92 | Pruning and grouping discovered association rules - TOIVONEN, KLMENTTINEN, et al. - 1995 |

90 | S.: Using general impressions to analyze discovered classification rules - Liu, Hsu, et al. - 1997 |

65 | Model-Directed Learning Of Production Rules - Buchanan, Mitchell - 1978 |

64 | Post-analysis of learned rules - Liu, Hsu - 1996 |

58 | Mining Surprising Patterns Using Temporal Description Length - Chakrabarti, Sarawagi, et al. |

52 | Autonomous discovery of reliable exception rules - Suzuki - 1997 |

37 | Discovery of actionable patterns in databases: The action hierarchy approach - Adomavicius, Tuzhilin - 1997 |

29 | Dynamic Itemset Counting and Implication Rules for - Brin, Motwani, et al. - 1997 |

23 | Selecting and Reporting what is Interesting The Kefir Application to Health Care - Matheus, Piatetshy–Shapiro, et al. |

19 | Learning problemsolving heuristics by experimentation - Mitchell, Utgoff, et al. - 1983 |

18 | Inductive learning of relational productions - Vere - 1978 |

16 | Interestingness and pruning of mined patterns - Shah, Lakshmanan, et al. - 1999 |

15 | Discovering unexpected patterns in temporal data using temporal logic - Berger, Tuzhilin - 1998 |

11 | Defining diff as a data mining primitive - Subramonian - 1998 |

9 | Data Mining for Fool’s Gold - Stedman - 1997 |

5 |
Pruning and summarizing the discovered rules
- LIU, HSU, et al.
- 1999
(Show Context)
Citation Context ...he heuristics that prune redundant rules from a discovered set of rules and does not explore the concept of minimality fully, nor proposes any algorithms for discovering a minimal set of patterns. In =-=[LHM99]-=- a technique is presented to prune and then summarize an already discovered set of association rules. In particular, [LHM99] defines the concept of direction-setting rules and demonstrates how nondire... |

3 | An Automatically Compliable Recognition Network for Structured Patterns - Hayes-Roth, Mostow - 1975 |

3 |
Discovering Unexpected Patterns in Data Mining Applications. Doctoral Dissertation
- Padmanabhan
- 1999
(Show Context)
Citation Context ... 2. Overview of Unexpectedness Unexpectedness of patterns has been studied in [ST95, ST96, LH96, LHC97, Suz97, CSD98, Sub98, BT98, PT98, PT99, P99] and a comparison of these approaches is provided in =-=[P99]-=-. In this paper we follow our previous approach to unexpectedness presented in [PT98, PT99, P99] because it is simple and intuitive (as it is based on a logical contradiction between a discovered patt... |