Intelligent System Comparing Clustering Algorithms to Recommend Sales Strategies

• Autores: Arévalo-Huaman, Gianella, Vallejos-Huaman, Jose, Burga-Durango, Daniel
• Formato: artículo
• Fecha de Publicación: 2024
• Institución: Universidad Peruana de Ciencias Aplicadas
• Repositorio: UPC-Institucional
• Lenguaje: inglés
• OAI Identifier: oai:repositorioacademico.upc.edu.pe:10757/675760
• Enlace del recurso: https://doi.org/10.1007/978-3-031-48858-0_17; http://hdl.handle.net/10757/675760
• Nivel de acceso: acceso embargado
• Materia: Customer Segmentation; E-commerce; K-means; Marketing Strategies; https://purl.org/pe-repo/ocde/ford#3.00.00

The context of the pandemic has accelerated the growth of electronic commerce in recent years. Consequently, there is intense competition among companies to boost sales and achieve success in a market environment where the failure rate stands at 80%. Motivated by this reason, an Intelligent System is proposed to recommend a sales campaign strategy within an e-commerce platform, automating the analysis of customer data by employing machine learning algorithms to segment (K-means) customers into groups based on their information. Additionally, the system recommends (Decision Tree) a specific sales strategy for each group. Therefore, the objective of this study is to analyze all the relevant aspects that arise in the relationship between an e-commerce business and its customers, as well as the effectiveness of generating strategies based on specific groups through Customer Segmentation. As a result, the system achieved a significant increase in Web Traffic, Click-through Rate, and Sales Revenue by 14%, 5%, and 10%, respectively, indicating a monetary growth and improved engagement after the utilization of our tool.