Statistics and Analytical Sciences
Product affinity segmentation discovers the linking between customers and products for cross-selling and promotion opportunities to increase sales and profits. However, there are some challenges with conventional approaches. The most straightforward approach is to use the product-level data for customer segmentation, but it results in less meaningful solutions. Moreover, customer segmentation becomes challenging on massive datasets due to computational complexity of traditional clustering methods. As an alternative, market basket analysis may suffer from association rules too general to be relevant for important segments. In this paper, we propose to partition customers and discover associated products simultaneously by detecting communities in the customer-product bipartite graph using the Louvain algorithm that has good interpretability in this context. Through the post-clustering analysis, we show that this framework generates statistically distinct clusters and identifies associated products relevant for each cluster. Our analysis provides greater insights into customer purchase behaviors, potentially helping personalization strategic planning (e.g. customized product recommendation) and profitability increase. And our case study of a large U.S. retailer provides useful management insights. Moreover, the graph application, based on almost 800,000 sales transactions, finished in 7.5 seconds on a standard PC, demonstrating its computational efficiency and better facilitating the requirements of big data.