Machine learning-based forecast modelling of dropped call rate in mobile networks: A random forest and support vector regression approach
1 Department of Computer Science, University of Cross River State, Calabar, Nigeria.
2 Department of Physics, Federal University, Otuoke, Nigeria.
Research Article
Open Access Research Journal of Science and Technology, 2025, 14(02), 162-171.
Article DOI: 10.53022/oarjst.2025.14.2.0107
Publication history:
Received on 06 July 2025; revised on 18 August; accepted on 21 August 2025
Abstract:
This study evaluates the historical performance and forecasts the DCR of Nigeria’s four major mobile networks: Airtel, 9mobile, Globacom, and MTN, using long-term monthly data from January 2015 to December 2024 obtained from the NCC. Two machine learning regression models, Random Forest Regression (RFR) and Support Vector Regression (SVR), were applied to predict DCR trends for 2024, with performance assessed using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE). Historical analysis revealed that Airtel, Globacom, and MTN consistently met the NCC benchmark, while 9mobile recorded only one month of non-compliance during the 132-month study period. Forecasting results showed that Random Forest outperformed SVR for Airtel, 9mobile, and Globacom, while SVR achieved superior accuracy for MTN. These findings demonstrate the potential of machine learning techniques as effective tools for network performance forecasting, supporting proactive fault management, capacity planning, and regulatory compliance in the Nigerian telecommunications sector.
Keywords:
Dropped Call Rate; Machine learning; Random Forest; Support Vector Regression; Forecast modelling
Full text article in PDF:
Copyright information:
Copyright © 2025 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0