The Effect of “Directness” of the Distance Metric to Produce Compact and Accurate Associative Classification Models

Machine learning techniques are ever prevalent as datasets continue to grow daily. Associative classification (AC), which combines and association rule mining algorithms, plays an important role in understanding big that generate a large number of rules. Clustering, on the other hand, can contribute by reducing space produce compact models. The above-mentioned facts were main motivation for this research work. We propose new distance (similarity) metric based “direct” “indirect” measures explain overall importance method, accurate Specifically, we aim employ agglomerative hierarchical clustering develop associative models contain lower Furthermore, strategy (based cluster center) is presented extract representative each cluster. Twelve real-world evaluated experimentally accuracy compactness, results compared those previously established classifiers. show our method outperformed algorithms terms classifier size most datasets, while still being classification.