A data-driven assessment of mobile operator service quality in Ghana

Abstract

The rapid proliferation of mobile services has increased the need for data-driven oversight of service quality, yet deriving insights from regulator-collected datasets remains challenging. This study demonstrates techniques to tap the rich potential of drive test measurement data for analytical regulatory and policy decision-making. Focusing on leading operator MTN in Ghana, we analyzed 4 years of drive test data supplied by the telecom regulator for the capital city of Accra. Three key performance indicators were evaluated—coverage, call setup time, and speech quality. We assessed service quality trends through statistical summaries, data visualization, and machine learning modeling and predicted speech quality scores. Our analysis revealed deteriorating performance post-2019 and found that the light gradient boosting machine algorithm provided the highest accuracy predictions of speech quality. Overall, this work showcases how regulators can capitalize on vast datasets using big data mining techniques to evaluate network conditions over time and geography, enhancing field measurements for oversight. Our approach and techniques provide a template for evidence-based policy-making to uphold consumer service quality as mobile networks evolve.