Analyzing Trie Graph-Based Apriori Algorithm

Finding meaningful patterns in big data is one of the active research in data mining. Market basket analysis (MBA) is one of the most helpful modeling techniques in data mining. It involves the mining and analysis of Association Rules. The association rules problem carried by the Apriori algorithm is represented in various issues ranging from market basket analysis, co-occurrence in natural language processing, behavioral similarity, and so on, representing the recognition of co-occurrence tendencies. The problem of the speed of combinatorial itemset acquisition from the Apriori algorithm in previous studies using memory (RAM) is still very possible to be studied. In this study, graph-based technology was chosen based on the study's results that graph algorithms are available (Neo4j'sNeo4j's graph data science or GDS) to support the process of obtaining association rules from the Apriori algorithm. The research used a network-based approach to mine transactional data and get detailed information about the products bought together in the market basket. The network-based approach gives insights into frequently purchased products and products, defined as "Communities." Then, we analyzed these groups of communities using different measures, such as Centrality and PageRank algorithms. From this study, we concluded that finding communities compared to the old traditional method of finding Association Rule is more giving broader information due to graph representation. The combination of the Trie data model and GDS algorithm can be used for further MBA research, specifically in the precision of frequent item set results.