Discovering Active and Profitable Patterns with Rfm (recency, Frequency and Monetary) Sequential Pattern Mining–a Constraint Based Approach

Sequential pattern mining is an extension of association rule mining that discovers time-related behaviors in sequence database. It extends association by adding time to the transactions. The problem of finding association rules concern with intratransaction patterns whereas that of sequential pattern mining concerns with inter-transaction patterns. Generalized Sequential Pattern (GSP) mining algorithm is a well known Apriori-based algorithm used for sequential pattern mining. The GSP algorithm suffers from several deficiencies whenever the database size is large, like: too many scanning of database when seeking frequent sequences and very large amount of candidate sequences generated unnecessary. These problems can be solved by applying various constraints in sequential pattern mining process. Constraint based sequential pattern mining discovers only those patterns which satisfy certain constraints; hence it improves the effectiveness and efficiency of sequential pattern mining process. Our proposed algorithm modifies the traditional sequential pattern mining algorithm GSP, so that, except the frequency two additional constraints, recency and monetary are considered to discover the RFM (Recent, Frequent and Monetary) sequential patterns. The advantage of considering these two additional factors is that this can ensure all patterns are recently active and profitable. Proposed approach works on time constraint. Proposed RFM sequential pattern mining approach discovers those sequential patterns from large database which are recent, frequent and which also satisfies monetary constraint.