Development of an efficient association rule classifier with temporal characteristics and hierarchical partitioning

Due to fast growth of temporal databases has made temporal data mining mandatory for knowledge discovery. Temporal association rule classification, a sub-task of temporal mining, integrates association rule mining and classification. The growth and increased complexities in temporal databases have necessitated this research work to propose techniques that enhance the process of associative mining and classification. Hierarchical partitioning with frequent pattern list with multiple projection pruning and 2-Step Associative rule Classification with Temporal characteristic (HM2ACT) is proposed to solve the issues and designed enhanced temporal association rule classification algorithm. The experimental results demonstrated that the proposed algorithm produces high quality rules and improved classification performance.