imported>Trappist the monk: /* top */ cite repair;

2021-04-15T12:58:18Z

top: cite repair;

New page

'''K-optimal pattern discovery''' is a [[data mining]] technique that provides an alternative to the [[frequent pattern discovery]] approach that underlies most [[association rule learning]] techniques.

Frequent pattern discovery techniques find all patterns for which there are sufficiently frequent examples in the sample [[data]]. In contrast, k-optimal pattern discovery techniques find the ''k'' patterns that optimize a user-specified measure of interest. The parameter ''k'' is also specified by the user.

Examples of k-optimal pattern discovery techniques include:
* k-optimal classification rule discovery.<ref>Webb, G. I. (1995). OPUS: An efficient admissible algorithm for unordered search. ''Journal of Artificial Intelligence Research'', 3, 431-465.</ref>
* k-optimal subgroup discovery.<ref>Wrobel, Stefan (1997) An algorithm for multi-relational discovery of subgroups. In ''Proceedings First European Symposium on Principles of Data Mining and Knowledge Discovery''. Springer.</ref>
* finding k most interesting patterns using sequential sampling.<ref>Scheffer, T., & Wrobel, S. (2002). Finding the most interesting patterns in a database quickly by using sequential sampling.
''Journal of Machine Learning Research'', 3, 833-862.</ref>
* mining top.k frequent closed patterns without minimum support.<ref>Han, J., Wang, J., Lu, Y., & Tzvetkov, P. (2002)
Mining top-k frequent closed patterns without minimum support. In ''Proceedings of the International Conference on Data Mining'', pp. 211-218.</ref>
* k-optimal rule discovery.<ref>Webb, G. I., & Zhang, S. (2005). K-optimal rule discovery. ''Data Mining and Knowledge Discovery'', 10(1), 39-79.</ref>

In contrast to k-optimal rule discovery and frequent pattern mining techniques, subgroup discovery focuses on mining interesting patterns with respect to a specified target property of interest. This includes, for example, binary, nominal, or numeric attributes,<ref>{{cite book | chapter=EXPLORA: A multipattern and multistrategy discovery assistant | url=http://publica.fraunhofer.de/documents/960183.html | access-date=2021-04-14|author=Kloesgen, W.|year=1996|title=Advances in Knowledge Discovery and Data Mining|pages=249-271}}</ref> but also more complex target concepts such as [[correlation]]s between several variables. Background knowledge<ref>{{cite conference |last1=Atzmueller |first1=Martin |last2=Puppe |first2=Frank |last3=Buscher |first3=Hans-Peter |title=Exploiting background knowledge for knowledge-intensive subgroup discovery |book-title=Proceedings of the 19th international joint conference on Artificial intelligence |publisher=Morgan Kaufmann Publishers |pages=647–652 |url=https://www.ijcai.org/Proceedings/05/Papers/1217.pdf |date=1 August 2005}}</ref> like constraints and [[Ontology (computer science)|ontological]] relations can often be successfully applied for focusing and improving the discovery results.

== References ==
<references/>

== External links ==

* {{cite web | title=Bringing you the state-of-the-art in Data Science | website=Bringing you the state-of-the-art in Data Science | date=2017-05-06 | url=http://giwebb.com/ | ref={{sfnref | Bringing you the state-of-the-art in Data Science | 2017}} | access-date=2021-04-14}}
* {{cite web | last=Atzmueller | first=Martin | title=VIKAMINE: Subgroup Discovery and Analytics | website=VIKAMINE | date=2015-05-17 | url=http://www.vikamine.org | access-date=2021-04-14}}

[[Category:Data mining]]

K-optimal pattern discovery - Revision history

imported>Trappist the monk: /* top */ cite repair;