Implementation of Upselling Model in Customer Relationship Management for Revenue Maximization in Telecommunications Industry

In this rapid era of business and commerce, it is crucial to build long-term customer relationships to maximize a company's revenue. To increase the growth and profitability of the telecommunications industry, up-selling strategies can be employed. In our research, we explore the use of predictive modeling and recommendation systems in Customer Relationship Management (CRM), with a specific focus on up-selling techniques. Utilizing a wide-ranging data set that includes various customer attributes, we employed six supervised machine learning techniques to create predictive models for the telecommunications industry around the world, namely XGBoost, HistGradientBoost, random forest, naive bayes, k-nearest neighbor and decision tree. We evaluated the performance of each model to reveal which algorithm performs best. We found that XGBoost turns out to be the most applicable and reliable model for upsell applications, with an accuracy of 0.96.