๐ Customer Segmentation using K-Means Clustering โ AI Internship @ SmartED Innovations One of the most practical ML problems in retail: who are your customers, really? For my minor project at SmartED Innovations, I built a complete customer segmentation pipeline using K-Means clustering โ identifying 5 distinct buyer personas from a 200-customer retail dataset. What the model found: โ ๐ข Cluster 3 โ High income + high spenders โ VIP targets for loyalty programmes โ ๐ต Cluster 1 โ High income + moderate spend โ Upsell candidates โ ๐ด Cluster 2 โ Low income + high spend โ Impulsive buyers, respond to flash sales โ ๐ Cluster 0 โ High income + low spend โ Conservative savers, need trust-building โ ๐ฃ Cluster 4 โ Low income + low spend โ Budget shoppers, discount-sensitive Technical pipeline: โ Feature selection: Annual Income + Spending Score โ StandardScaler for feature normalisation โ Elbow Method to determine optimal k=5 โ K-Means++ initialisation for stable convergence โ Seaborn scatter plot with centroid markers for visual validation Tech: Python ยท pandas ยท scikit-learn ยท matplotlib ยท seaborn ๐ GitHub: github.com/iamadhitya1/customer-segmentation-retail #MachineLearning #Python #KMeans #CustomerSegmentation #DataScience #UnsupervisedLearning #RetailAnalytics #AIInternship #SmartEDInnovations #IITRAM