ISSN (PRINT): 2393-8374, (ONLINE): 2394-0697, VOLUME-3, ISSUE-1, 2016 57 ASSOCIATION RULE MINING: A DATA PROFILING AND PROSPECTIVE APPROACH Hemant Kumar Soni 1 , Sanjiv Sharma 2 , Pankaj K. Mishra 3 1 Asst. Prof., Dept. of Computer Science, ASET, Amity University, Gwalior (M.P) 2 Asst. Prof., Dept. of Computer Science, MITS, Gwalior (M.P) 3 Asst. Prof., Dept. of Applied Science, ASET, Amity University, Gwalior (M.P) Email:soni_hemant@rediffmail.com 1 Abstract The Main objective of data mining is to find out the new, unknown and unpredictable information from huge database, which is useful and helps in decision making. There are number of techniques used in data mining to identify frequent pattern and mining rules includes clusters analysis, anomaly detection, association rule mining etc. In this paper we discuss the main concepts of association rule mining, their stages and industries demands of data mining. The pitfalls in the existing techniques of association rule mining and future direction is also present. Keywords: Association Rule Mining, Frequent Pattern, Apriori, FP-Tree, Incremental data mining, support, confidence. Introduction Data Mining is the iterative and interactive process of discovering valid, novel, useful, and understandable and hidden patterns. Data Mining is used in extracting valuable information in large volumes of data using exploration and analysis. With an enormous amount of data stored in databases and data warehouses requires powerful tools for analysis and discovery of frequent patterns and association rules. In data mining, Association Rule Mining (ARM) is one of the important areas of research, and requires more attention to explore rigorously because it is an prominent part of Knowledge Discovery in Databases (KDD). Application area of data mining is very vast, such as Remote Sensing, Geographical Information System, Cartography, environmental assessment & planning a name of few. Association Rule Mining Recently, researchers are applying the association rules to a wide variety of application domains such as Relational Databases, Data Warehouses, Transactional Databases, and Advanced Database Systems like Object- Relational, Spatial and Temporal, Time-Series, Multimedia, Text, Heterogeneous, Legacy, Distributed, and web data [1]. Since data generated day by day activities, the volume of data is increasing dramatically. Massive amount of data is available in the data warehouses. Therefore, mining association rules helps in many business decision making processes. Some examples are cross-marketing, Basket data analysis and promotion assortment etc. In the area of association rules mining, a lot of studies have been done. The association rules mining first introduced in [2] [3] [4]. For a given transaction database T, An association rule is an implication of the form X ⇒ Y, where X ⊂ I, Y ⊂ I, and X ∩ Y = Φ, i.e. X and Y are two non-empty and non-intersecting itemsets. The rule X ⇒ Y holds in the transaction set D with confidence c if c % of transactions in T that contain X also contain Y. A transaction T is said to support an item ik, if ik is present in T. T is said to support a subset of items X ⊆ I, if T support each item ik in X. An itemset X ⊆ I have a support s in D. It is denoted by s(X). If s% of transactions in D support X.