Frequent itemset mining for Big data

Frequent itemset mining is the technique used mostly in field of data mining like finance, health care system. We are focusing on methodologies for extracting the useful knowledge from given data by using frequent itemset mining. Most important use of FIM is customer segmentation in marketing, shopping cart analyzes, management relationship, web usage mining, and player tracking and so on. Association rule is for finding the frequently occuring group of item in shopping cart. In this paper, we are investigating FIM techniques applicability on the Map Reduce platform. In FIM, we are using two parallel algorithms, Dist-eclat and Big-FIM algorithms. Where, Dist-eclat algorithm is mainly work on speed purpose while Big-FIM algorithms mainly focuses on optimization on big-data.. So for mining large amount of datasets, two new methods are introduced: First, Dist-Eclat focuses on speed while second Big-FIM is running on really huge datasets for optimization. In our paper we are showing the scalability of our methods. Using these methods, considering customer behavioral analysis of buying product, we are giving suggestion with the customer choosen product, so the retailer business benefits is maximized at high level.