Machine Learning Approach to Users’ Age Prediction: A Telecom Company Case Study in Saudi Arabia

Abstract

The accurate prediction of demographic attributes of users, including age and gender, is a pivotal challenge in personalized search, ad targeting, and other related fields. This information enables companies to refine their target audience and enhance the overall user experience and quality of service (QoS). Among these, the Saudi Telecommunication Company (STC), a premier telecommunications provider in Saudi Arabia, Middle East, and Africa, recognizes the substantial role of age-prediction systems. This study, therefore, explores the application of machine learning (ML) techniques to predict user age, thus assisting in the delivery of age-appropriate ads and offers. We utilized a dataset provided by STC, comprising three million samples with key user and device features. Four ML algorithms were employed in this analysis: the Artificial Neural Network (ANN), Random Forest (RF), Gradient Boosting (GB), and Decision Tree (DT). These models were compared and evaluated based on their predictive performance. The ANN emerged as the optimal classifier, achieving an accuracy of 60%, comparable to similar studies conducted within the telecommunications industry. The implications of these findings suggest that ML techniques can effectively predict user information, thereby enabling service providers to tailor their offerings to the specific age demographics of their users. The findings from this study contribute to the broader understanding of user age prediction and its practical implications for telecommunications companies. Future research could extend this work by exploring other demographic prediction challenges and applying the ML approach to other sectors.