Customer Segmentation using Machine Learning

Abstract

Customer segmentation has seen major growth in all sectors in the last decade. Several techniques have been devised to analyze customer behavior through loyalty, purchases, recency, frequency and monetary to develop efficient marketing strategies that cater to each client individually. As the availability of products and services increases, so does the competition. With the spiraling of automation accompanied by its cost-effectiveness and ease of availability, all businesses equip themselves with the required workforce and machinery to conduct experiments such as customer segmentation on an industrial scale. In the proposed work, the datasets are manipulated by extracting features from existing attributes. A widespread approach is RFM that calculates the Recency, Frequency and Monetary values for each customer tuple. This paper aims at laying out a new approach at every step of customer segmentation from pre-processing, clustering, validation and suggesting marketing strategies for customer retention. Two datasets-Online Retail II Set and Mall Customer Segmentation are modelled and the results from analysis of both the datasets are presented and compared to reach a generalized opinion.