Improving Customer Experience in Supermarkets: A New Approach based on Travel Path
Abstract
In today’s competitive market, understanding its customers is a key to the success of any business. The market contains various customer subgroups that can be distinguished based on purchasing habits, time spent, product selection and travel path. To identify the pattern hidden inside these subgroups is needed to use real data as it reflects the ordinary behaviour of the customers. Analysis of the travel path data that customers make inside the shopping mall enables retailers to understand and predict customer behaviour, which has become a critical point in effective decision making for increase sales with more customer comfort. Introducing right discount for the right products play as an important mediating factor in relationship between customer Traditional methods in determining the discount and layout have dealt only with customer transactions which miss important other characteristics of customer’ purchasing behaviour. This paper addresses the problem of sales increase based on personalized discount schemas and improved store layout using customer’s shopping travel path. It uses the Frequent Pattern Growth (FP Growth) algorithm to improve the sales and the RFM (Recency, Frequency, Monitory value) analysis to identify the customer segments based on the dataset of Instacart from the Kaggle website. FP growth algorithm has been used to identify the frequent locations and frequent products of customer’s purchases. An improved version of the supermarket layout has been suggested based on the frequent travel path of customers. The findings of this approach can be used by retailers to improve the in-store shopping experience of customers.
