Data-Driven Customer Segmentation Using Clustering Methods for Business Success

Abstract

In today’s dynamic and highly competitive business environment, it is important to possess an in-depth understanding of different customer preferences and the ability to address them to achieve long-term success competently. Using data-driven customer segmentation has become a prominent method for extracting practical insights from extensive datasets and subsequently customizing marketing campaigns. This paper thoroughly examines the utilization of clustering techniques for data-driven customer segmentation, aiming to augment business performance. The open-source Kaggle dataset is utilized for performing the experimentations. Customer segmentation is achieved by utilizing two clustering algorithms, namely K-means and Louvain clustering. The outcomes of both algorithms are compared to determine the optimal number of clusters and evaluate the efficacy of the clustering techniques. In K-means clustering, the Silhouette method is used to identify the best number of clusters. The results prove that the Louvain clustering performs better than the K-means for segmenting the customers with fewer outliers. Also, the best number of groups (clusters) identified by both algorithms is five. Thus, the proposed technique can be utilized in real-time to improve the business by adopting specific marketing strategies for specific groups.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 11 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.