Implementation & Analysis of Online Retail Dataset Using Clustering Algorithms

The application of clustering algorithms for client segmentation in online shopping is investigated in this paper. Customer segmentation is a common method used by organisations to categorise consumers based on their traits and behaviour, enabling them to target particular groups with their marketing and sales tactics. Clustering algorithms are useful tools for consumer segmentation since they classify clients according to shared traits or behaviours. However, picking the best method for a particular dataset may be difficult, and segmentation performance may vary depending on the algorithm selected. In this study, the efficacy of three clustering algorithms-K-means clustering, hierarchical clustering, and DBSCAN-for client segmentation in online shopping is compared. We assess the algorithms using a number of criteria, such as the Davies-Bouldin index, the silhouette score, and the Calinski-Harabasz index. Our findings highlight the advantages and disadvantages of each algorithm and pinpoint client groups with particular tendencies. By offering useful advice for companies wishing to adopt consumer segmentation using clustering algorithms, this paper contributes to the subject of client segmentation in online retail.