| dc.description.abstract |
In this study, it is aimed to develop a user-friendly, interactive web software for association rules mining. In the developed software, among the association rule methods; Filtered Associatior, Apriori, Frequent Pattern Growth, Predictive Apriori, Generalized Sequential Patterns, HotSpot, Tertius algorithms are used. In addition, association rules algorithms have certain limitation(s) regarding the structure of the data set. Therefore, preprocess menu in the software includes missing value assignment and variable type conversion, methods. In order to evaluate the association rules, support and confidence criteria are present in the software. However, it is not always possible to distinguish interesting and important rules only according to criteria of support and confidence. Therefore, in the proposed software; leverage, lift and conviction criteria are also included. A medical application is performed by using association rules mining, and the experimental results are evaluated based on the outputs of the developed software. |
|