Utilizing Non-redundant Association Rules from Multi-level Datasets

Association rule mining and recommender systems are two popular methods for obtaining knowledge and information from datasets. However, both of these methods suffer from limitations. Traditionally association rule mining has focused on extracting as many rules as possible from flat datasets. More recently, issues over the number of rules and obtaining rules from datasets with multiple concept levels have come into focus. Recommender systems have been popular with users when it comes to helping find similar interests to those they already have. However, recommender systems suffer from two major problems, cold start and novelty. The aims of our research is to develop an approach for extracting non-redundant multi-level and cross-level association rules from datasets with multiple concept levels and utilise them in a recommender system with the aim of potentially solving the cold start and novelty problems.