Publication

Abstract : In this paper, an attempt is made towards interpretation of customer’s buying patterns which is most widely useful for improving their satisfaction during their shopping in large shopping malls or stores. One of the significant aspects focused in this work is to value the customer needs and improve the level of customer satisfaction through analyzing their varied purchase patterns from time to time. The prediction of correlation between the type of items the customer’s opting in terms of various factors like brand, model, cost, their budget, demographics attributes, frequently shopped products and regular/consistent brands etc, the organization can make better attempts on designing the strategies for alignment of products/items in their shelves so that customer fulfill their needs with minimal risk. Also, the organization can improve the productivity of items/products which are at high demand along with modeling of new marketing strategies. The prediction of frequently sold products of certain brands can be used as basis for design of attractive offers assisting the sales of non frequently used brands so that the demand can be improved. Datasets on whole customer information is employed for experimentation comprised of 8 attributes including region, channel and various other food categories and about 440 instances. The visualization of datasets is carried out using Weka tool and overall summarization of data is carried out using attribute wise with respect to various food item categories. © IAEME Publication.