Research on the Mall Customers Segmentation Based on K-means and DBSCAN

Studying customer classification of a shopping mall is important to understand the demographics, behavior, and preferences of customers, which can help in designing effective marketing strategies and improving customer experience to increase sales and revenue. It can also help in optimizing product placement and inventory management to cater to the needs of different customer segments. Based on the research background, the paper uses k-means and DBSCAN to classify mall customers, according to which the data is divided into 5 clusters and 6 clusters according to the elbow chart and K-mean, and the DBSCAN also divides the data into 6 clusters, but through the data ratio to the discovery, the cluster effect is not as good as the k-Mean effect. And in the final grouping based on k-means results, this article provides a business analysis of the 6 characteristic clusters, assumes 2 situations, and proposes solutions and optimization for these 2 situations that are conducive to the trader’s improvement of the commodity and sales environment as a reference basis, thereby increasing trader’s turnover, while also increasing consumer satisfaction and consumption effort.