A Customer-Centric Approach for Recommending Products: A Case Study of Digikala

Abstract

As competition among marketing companies and retailers intensifies, segmenting customers and recommending suitable products has become a critical strategy for maintaining a competitive edge. With the rapid growth of online shopping, customers often make purchasing decisions based on their needs and desires. Salespeople play a crucial role in influencing customers, making a product recommendation system essential. Such a system has various applications and can also encourage customers to purchase additional products. In this study, we present a method for recommending products to customers that utilizes the K-means clustering algorithm and the RFM (Recency, Frequency, Monetary) model to segment customers and make personalized product recommendations. To evaluate the performance of the proposed system, we conducted experiments using data collected from Digikala, an online shopping company. The results show that clustering based on the RFM features has better results for cluster number zero, which represents loyal customers. Therefore, to encourage these customers to purchase higher-priced goods, companies can offer special discounts to cluster number zero. Our approach provides a customer-centric solution for increasing sales and customer satisfaction.

Keywords

• rfm model
• k-means clustering algorithm
• customer segmentation
• digikala online company
• recommender system