Customer Analytics using Surveillance Video

TL;DR

This paper tackles the problem of extracting purchase-relevant information from surveillance video to map customers to garments they show interest in. It introduces an extended MCOKE framework that leverages weighted $k$-Means initialization to form garment-centered clusters and permits overlapping memberships across frames via a $maxDist$ threshold and a $mindist$ rule for re-clustering. The approach integrates demographic data (age and gender), time spent, garment color preferences, and expressions to enable demographic-aware sales analytics and targeted marketing. Experiments on a real retail dataset demonstrate insights into gender- and age-related shopping patterns and offer practical implications for merchandising, layout optimization, and demand forecasting.

Abstract

The analysis of sales information, is a vital step in designing an effective marketing strategy. This work proposes a novel approach to analyse the shopping behaviour of customers to identify their purchase patterns. An extended version of the Multi-Cluster Overlapping k-Means Extension (MCOKE) algorithm with weighted k-Means algorithm is utilized to map customers to the garments of interest. The age & gender traits of the customer; the time spent and the expressions exhibited while selecting garments for purchase, are utilized to associate a customer or a group of customers to a garments they are interested in. Such study on the customer base of a retail business, may help in inferring the products of interest of their consumers, and enable them in developing effective business strategies, thus ensuring customer satisfaction, loyalty, increased sales and profits.

Figures (6)

• Figure 1: Workflow of the proposed Framework
• Figure 2: Some of the sales videos in the dataset
• Figure 3: Customer's based on gender and age-group
• Figure 4: Average time spent in store
• Figure 5: Expression exhibited by customers, for a particular colour of garments of interest