Algorithm for classification based on positive and negative class association rules

Luo Junwei, Luo Huimin
2010 2010 3rd International Conference on Computer Science and Information Technology  
The negative class association rules are important to build accurate and efficient classifiers. Despite a great deal of research, a number of challenges still exist. In order to solve the problem of "difficult to build precise classifier", the paper presents a new algorithm for classification which integrates positive class association rules and negative class association rules. The algorithm applies Apriori method and correlation between itemsets and class labels to compute all positive and
more » ... ative class association rules from training dataset. Moreover, a classifier will be built to predict the label of a new data object. The performance study shows that the method is highly efficient and accurate in comparison with other reported associative classification methods.
doi:10.1109/iccsit.2010.5564641 fatcat:dzjk6c3b3rafbn5z74tm2gyr6y