The primary aim of this project is to apply advanced data analytics using PySpark techniques to gain a deeper understanding of mall customers and their shopping behaviors.
Customer Segmentation: The clustering process categorized mall customers into five distinct segments. These segments provide a deeper understanding of customer behaviors and preferences based on gender, age, annual income, and spending score.
Cluster Insights
Cluster 1: Customers in this group have relatively low annual incomes but are willing to spend, indicating potential for targeted promotions and loyalty programs.
Cluster 2: High-income customers with very high spending scores represent valuable shoppers who may respond well to premium offerings.
Cluster 3: Customers in this cluster exhibit moderate income and moderate spending patterns, making them a balanced target for marketing strategies.
Cluster 4: High-income shoppers with very high spending scores, suggesting opportunities for upscale products and personalized experiences.
Cluster 5: Customers in this cluster have lower income and spending scores, indicating more conservative spending habits.
Silhouette Score: The calculated Silhouette score of approximately 0.6276 indicates that the clusters are well-defined and provide meaningful insights.
With these customer segments, the mall can tailor marketing campaigns, product offerings, and promotions to better meet the needs and preferences of each cluster. This personalization can lead to improved customer engagement and increased sales.