Customer Segmentation for Smooth Shopping Experience

Abstract

This paper presents a model or a system for segmentation of customers based on their past activity or shopping history. Due to increased demand for online shopping local customers are being affected on a large scale .So there is a necessity in achieving targeted marketing which local shops can use to attract their customers .Customer segmentation refers to the process of segmenting the customers with same kind of behaviors into the similar segment with distinct patterns into diverse segments. This proposed model will basically divide the customers into clusters based on the category of items that they have purchased. For categorization or segmentation several parameters like customer’s age, class( rich or poor)and their expenses has been taken into consideration. This approach will basically help the shopkeepers in achieving what is called as targeted marketing. The current approaches of dividing the customers doesn’t have a simple and drastic solution for the same. Most of the existing solutions have used only k-means clustering for dividing the customers. The approach presented in this paper uses five different algorithms namely k-means clustering, Agglomerative clustering, Density Based Spatial clustering, Mean Shift clustering and Balanced Iterative Reducing and Clustering using Hierarchies to compare their results using Silhouette Coefficient and Davis Bouldin Index.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 7 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.