Integrated Intelligent Research (IIR) International Journal of Data Mining Techniques and Applications Volume: 07, Issue: 01, June 2018, Page No.100-110 SSN: 2278-2419 100 Application of Utility Mining using Frequent Itemset and Association Rules: A Survey T.Indhumathy 1 , T.Velmurugan 2 1 Research Scholar, 2 Associate Professor PG and Research Department of Computer Science, D. G. Vaishnav College, Arumbakkam, Chennai, India E-Mail: tindhu_m3@yahoo.com, velmurugan_dgvc@yahoo.co.in Abstract: Mining on data reveals patterns that provide useful information for analysis, decision making and forecasting in various domains. Association Rule Mining (ARM) identifies patterns on itemsets which are either frequent or have interesting relationship amongst them based on strong rules and conceptually form a basis for Frequent Itemset mining (FIM) problems. FIM extracts binary values from transaction databases to identify frequently bought items but provides insufficient information for identifying infrequent items that generate maximum profit. So a latter problem, High utility itemsets (HUI) mining was developed to focus on the itemsets that generate huge profit to the business. Even though HUI is related to Business Intelligence, its application extends to Web Server Logs, Biological Gene Databases, Network Traffic Measurements and many other fields. This paper presents a survey on the algorithms from different aspects and perspectives based on Utility mining, Frequent Itemset generation and Association Rule Mining. Keywords: Association Rule mining, Frequent Itemset Mining, Maximum Profit, High Utility Mining I. INTRODUCTION Originating from machine learning and artificial intelligence, Data mining is a powerful technology that extracts hidden effective information automatically from large data repositories, named as knowledge discovery in databases (KDD). Data Mining is a conglomeration of different disciplines such as statistics, database systems, information science, and business intelligence to name a few. Depending upon the type of data, various techniques and mathematical algorithms such as fuzzy set theory, neural networks, inductive logical programming, signal processing, image analysis, bioinformatics, web technology, computer graphics, business, economics and psychology may be applied. Upon the application of a specified techniques or retrospective tools on large volumes of data, otherwise called information processing (i.e., collection, extraction, warehousing, analysis), hidden meaningful patterns are revealed. These patterns allow businesses to make proactive knowledge driven decisions that were traditionally too time consuming to resolve. Data mining tasks are categorized as predictive which focus and infer on the current data and descriptive which work on the general properties of data.Utility mining, FIM and ARM are predictive, revealing useful interesting patterns and relationship among the data related not only to Business Intelligence but also to Medical Science, Security, Telecommunications, Census Analysis and Text Analysis. Different kinds of frequent patterns such as Itemsets, Subsequences or Substructures are extracted mainly from transactional or relational databases. To uncover interesting associations, correlations and recurring relationship amongst them, the output representation such as classification rules, association rules, expressive rules or any other strategy is adopted and different techniques to generate these patterns are developed. The problem of mining association rules was implemented as AIS algorithm by Rakesh Agrawal, Tomasz Imieliński and Arun Swami in 1993 [1]. The researchers use basket data (Market Basket Analysis also known as Affinity Analysis) referring to point-of-sale transaction and analyses customer buying habits by finding association between the different items. It eventually helps the retailers develop marketing strategies by gaining insight into frequently bought items. With a measure of support and confidence, the algorithm decomposes the problem into two major subtasks. 1) To find all the frequent itemsets that satisfy the minimum support threshold is the first task. 2) The second task is Rule Generation, where all the high-confidence rules known as strong rules from the frequent itemsets are extracted.