VALIDATION OF KEY PERFORMANCE INDICATORS OF MOBILE TELECOMMUNICATION OPERATORS USING ENSEMBLE MODELS AND ARTIFICIAL NEURAL NETWORKS WITH NIGERIAN COMMUNICATION COMMISSION’S THRESHOLDS

Abstract

This paper presents the comparative studies among the predictive models used for the validation of the key parameter indicators of mobile network operators with the Nigerian Communication Commission’s threshold. Four Key Performance Indicators were predicted using artificial neural networks and ensemble models which include bagging and LSBoost models. The Key Performance Indicators and weather parameters for six locations in Southwestern Nigeria were employed. MATLAB R2020a was employed to develop the three models. Microsoft Excel was used in the analysis of the dataset. The bagging model gave the best average compliance of 94% and 100% for CSSR and TCH Congestion Rate respectively while the ANN model yielded the best average compliance of 76.7% and 85.2% for DCR and SDCCH Congestion Rate respectively.