Buchter, O. and Wirth R. Discovery of association rules over ordinal data: a new and faster algorithm and its application to basket analysis, in [30], 36-47, 1998. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
An Analysis of Quantitative Measures Associated with Rules - Yao, Zhong (1999) (Correct)
....(a b) b d) 20) This measure is closely related to the divergence measure proposed by Kullback and Leibler [12] 3.3 Two way support The measure of independence IND has been used by many authors. Silverstein et al. 27] referred to it as a measure of interest. Buchter and Wirth [3] regarded it as a measure of dependence. Gray and Orlowska [10] used the same measure, and provided the interpretation given by equation (9) The measure of two way support corresponding to equation (14) is given by Yao and Liu [31] as: S 2 (E, H) G(E H) log IND(E,H) 21) By ....
Buchter, O. and Wirth R. Discovery of association rules over ordinal data: a new and faster algorithm and its application to basket analysis, in [30], 36-47, 1998.
Analysing Warranty Claims of Automobiles - An Application.. - Hipp, Lindner (1999) (Correct)
....of claims connected to the alternator typically lead to a complete exchange of the corresponding cables but not already the rst or second of such claims, this dependency might remain undetected. Quantitative association rules were rst described in [10] and we use the algorithm Q2 from [5] to mine such rules. 5.5 Sequential Patterns Some of the business questions aim on dependencies that take time into consideration. e.g. we want to know if repairs of special parts imply future claims of the same or other parts. So called sequential patterns are an extension of association rules ....
O. Buchter and R. Wirth. Discovery of association rules over ordinal data: A new and faster algorithm and its application to basket analysis. In Research and Development in Knowledge Discovery and Data Mining (Proceedings of the Second Pacic-Asia Conference on Knowledge Discovery and Data Mining, PAKDD-98), Melbourne, Australia, April 1998.
Knowledge Discovery and Interestingness Measures: A Survey - Hilderman, Hamilton (1999) (12 citations) (Correct)
....excellent scaleup behaviour and requires only minimal additional overhead compared to serial Apriori. Other literature focuses on alternative approaches for discovery of association rules. These approaches include Hybrid Distribution [28] Itemset Clustering [69] Share Measures [30] and Q2 [10]. Hybrid Distribution is a parallel algorithm that improves upon parallel Apriori by dynamically partitioning the candidate itemsets to achieve superior load balancing across the nodes. More association rules can then be generated more quickly in a single pass over the database. Scaleup is near ....
O. Buchter and R. Wirth. Discovery of association rules over ordinal data: a new and faster algorithm and its application to basket analysis. In X. Wu, R. Kotagiri, and K. Korb, editors, Proceedings of the Second Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'98), pages 36--47, Melbourne, Australia, April 1998.
On Pruning Strategies for Discovery of Generalized and.. - Weber (Correct)
....combine intervals with a common parent in one itemset, because such combinations are either empty or equivalent to their common descendants. If the partitioning of numerical attributes takes place in advance or at the very beginning of the search process (which is commonly the case, Q2, see below, [2] is an exception) the interval boundaries can serve as items instead of the intervals themselves. Figure 2(b) depicts an item space where items represent interval boundaries instead of intervals. Again, the frequency of an item i is at most the frequency of its ancestor. Dotted arrows indicate ....
....support, and treats these as frequent 1 itemsets within the Apriori algorithm. Qar avoids generating candidate itemsets that contain more than one interval of the same numerical attribute, but makes no further use of the generality ordering among the intervals for pruning candidates. 3. 2 Q2 Q2 [2] consists of two phases. In the initial phase, the basic Apriori algorithm determines all frequent itemsets, thereby ignoring numerical information and treating numerical attributes as Boolean attributes. Having found all frequent itemsets in the Boolean setting, Q2 generates candidates that take ....
[Article contains additional citation context not shown here]
O. Buchter and R. Wirth. Discovery of association rules over ordinal data: A new and faster algorithm and its application to basket analysis. In Proc. PAKDD-98, 1998.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC