In today's business world there is excess of available data & a great need to make good use of it. Data mining is art of extracting pattern and knowledge from large amount of data. Frequent itemset plays essential role in many Data Mining tasks that try to find out interesting patterns from database such as association rules. Association rule mining is a method of discovering interesting correlations between variables in large databases. Mining of frequent itemset is most popular problem in

more »

... mining. The discovery of frequent itemsets can be serve valuable economic & research purpose. But valuable discovered frequent itemsets should not only assure security but also achieve high data utility & offer time efficiency. The frequent itemsets are patterns or items like itemset, substructures or subsequences that comes out in data set frequently. There are several FIM algorithms for frequent item mining such as Apriori, FPgrowth, Eclat, UP growth algorithms. To provide security or privacy here we use differentially private FIM algorithm using UP-growth algorithm. It consist of Prepocessing & mining phase.In prepocessing phase, to enhance utility & privacy advance smart splitting method is proposed to transform database. For given Database preprocessing phase should be performed only once. In mining phase run time estimation & dynamic reduction performed. To cover the information loss by smart splitting, we contrive run time estimation to calculate actual support of itemsets in original database. For privacy we have added noise in the database, we put forward dynamic reduction method to reduce the noise dynamically which guarantees privacy during mining process. In this paper we proposed new algorithm for mining high utility itemsets called as UP growth which consider not only frequency of itemset but also utility associated with the itemset.