Publications

Abstract : The purpose of this research is to perform infrequent pattern mining on ECommerece Data. Association mining is an interesting model of data mining which is responsible for retrieving correlations, frequent patterns and infrequent associations from large datasets. The main objective of infrequent pattern mining is to discover the top infrequent items from the positive and negative association patterns with minimum support and confidence measures. Generally, association rule mining process is processed in 2 phases. Initially itemsets having high threshold values are identified and then secondly generates association patterns from these frequent candidate sets. Association rules can be represented in two forms, one is positive association rules and the other is negative association rules. In this proposed approach, user recommended frequent and infrequent mining model was developed to discover the top frequent and infrequent relational patterns on the e-commerce dataset. User selects his feature product to generate frequent and infrequent association patterns. Based on the feature product, all related candidate sets are generated to the user selected feature product P. These candidate sets are used to discover the frequent and infrequent associations with other feature products. Here weighted infrequent rankingmeasure was used to filter the infrequent product from the frequent associations.Experimental results show that proposed model has high computational prediction compared to traditional infrequent mining models.