Method and system for mining frequent and in-frequent items from a large transaction database

Abstract

The technique relates to a system and method for mining frequent and in-frequent items from a large transaction database to provide the dynamic recommendation of items. The method involves determining user interest for an item by monitoring short item behavior of at least one user then selecting a local category, a neighborhood category and a disjoint category with respect to the item clicked by the at least one user based on long term preferences data of a plurality of users of the ecommerce environment thereafter selecting one or more frequent and infrequent items from each of the selected local, neighborhood and disjoint category items and finally generating one or more dynamic recommendations based on the one or more items selected from the local category, the neighborhood category and the disjoint category and the one or more selected frequent and infrequent items.