Abstract

The prediction of the signal strength of cellular networks has become a critical area of research with the deployment of 4G, LTE, and 5G technologies. Telecom operators can optimize the coverage areas, reduce call drops, and enhance user experience through accurate prediction of received signal strength. Complex environmental factors are ignored in traditional signal propagation models. Recently, various machine learning techniques have been applied to predict the signal strength of cellular networks, as their data-driven insights can adapt to dynamic network conditions. This paper explores several machine learning algorithms to build an optimal model that more accurately predicts the signal strength of cellular networks. The dataset used in the research was collected from Kaggle online dataset repository. It was divided into two partitions: a training set consisting of 80% of the data and a test set containing the remaining 20%. Then, different regression algorithms: K-Nearest Neighbors (KNN), Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGB) were applied to the dataset. Finally, the RF and XGB models achieved the optimal performance i.e., the lowest MAE and RMSE values and the highest R2 value. The knowledge extracted from these models can be used as a decision-making tool for telecom operators and organizations to accurately predict the signal strength of cellular networks in specific areas in the future.

References

• Hata, M. (2013). Empirical formula for propagation loss in land mobile radio services. IEEE transactions on Vehicular Technology, 29(3), 317-325.
• Nkordeh, N. S., Atayero, A. A. A., Idachaba, F., and Oni, O. (2014, July). Lte network planning using the hata-okumura and the cost-231 hata pathloss models. In Proceedings of the World Congress on Engineering (Vol. 1, pp. 2-4). London: WCE.
• Salous, S., Lee, J., Kim, M. D., Sasaki, M., Yamada, W., Raimundo, X., and Cheema, A. A. (2020). Radio propagation measurements and modeling for standardization of the site general path loss model in International Telecommunications Union recommendations for 5G wireless networks. Radio Science, 55(1), 1-12.
• Sector, R. (2023). Report ITU-R F. 2323-2.
• Osahenvemwen, A. O., and Omatahunde, B. E. (2018). Impacts of weather and environmental conditions on mobile communication signals. Journal of Advances in Science and Engineering, 1(1), 33-38.
• Karanja, H. S., Misra, S., and Atayero, A. A. A. (2023). Impact of mobile received signal strength (RSS) on roaming and non-roaming mobile subscribers. Wireless Personal Communications, 129(3), 1921-1938.
• Tomic, I., Bleakley, E., and Ivanis, P. (2022). Predictive capacity planning for mobile networks—ML supported prediction of network performance and user experience evolution. Electronics, 11(4), 626.
• Azoulay, R., Edery, E., Haddad, Y., and Rozenblit, O. (2023). Machine learning techniques for received signal strength indicator prediction. Intelligent Data Analysis, 27(4), 1167-1184.
• Mallik, M., and Villemaud, G. (2025, May). Deep Learning Based Received Signal Strength Estimation. In ICMLCN 2025-IEEE International Conference on Machine Learning for Communication and Networking.
• Chandrasekaran, G., Ergin, M. A., Yang, J., Liu, S., Chen, Y., Gruteser, M., and Martin, R. P. (2009, June). Empirical evaluation of the limits on localization using signal strength. In 2009 6th Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks (pp. 1-9). IEEE.
• Ali, M. A., and Khan, S. (2020). Analysis of Signal Strength Metrics in Cellular Networks. International Journal of Wireless Communications, 12(3), 45–52.
• Ali, M. A., and Khan, S. (2021). Predicting Cellular Network Signal Strength Using Machine Learning Techniques. Journal of Telecommunications and Information Technology, 15(4), 78–85.
• Afolabi, I., Taleb, T., Samdanis, K., Ksentini, A., and Flinck, H. (2018). Network slicing and softwarization: A survey on principles, enabling technologies, and solutions. IEEE Communications Surveys & Tutorials, 20(3), 2429-2453.
• Fauzi, M. F. A., Nordin, R., Abdullah, N. F., and Alobaidy, H. A. (2022). Mobile network coverage prediction based on supervised machine learning algorithms. Ieee Access, 10, 55782-55793.
• Wang, X., Zhang, Y., and Li, Z. (2022). A hybrid deep learning model for signal strength prediction in cellular networks. IEEE Transactions on Wireless Communications, 21(5), 3456–3469. https://doi.org/10.1109/TWC.2022.3145678
• Chen, Y., Zhang, M., and Li, Y. (2021). Graph neural networks for network coverage estimation in cellular systems. IEEE Journal on Selected Areas in Communications, 39(12), 3765–3777. https://doi.org/10.1109/JSAC.2021.3084567
• Kusiak, A. (2002, March). Data mining and decision making. In Data Mining and Knowledge Discovery: Theory, Tools, and Technology IV (Vol. 4730, pp. 155-165). SPIE.
• Md. Humayun Kabir. “Study on the Performance of Classification Algorithms for Data Mining". IOSR Journal of Computer Engineering (IOSR-JCE) 21.3 (2019): 23-30.
• A.S.M. Sabiqul Hassan, Syed Maruful Huq, Mohammad Kamal Hossain Foraji, Md. Humayun Kabir . Study on the Performance of Supervised Machine Learning Algorithms in Mobile Price Range Classification. International Journal of Computer Applications. 187, 1 (May 2025), 39-45. DOI=10.5120/ijca2025924768
• Kaggle. "Cellular Network Analysis Dataset". url: https://www.kaggle.com/datasets/suraj520/cellular-network-analysis-dataset
• Potdar, K., Pardawala, T. S., and Pai, C. D. (2017). A comparative study of categorical variable encoding techniques for neural network classifiers. International journal of computer applications, 175(4), 7-9.
• Patro, S. G. O. P. A. L., and Sahu, K. K. (2015). Normalization: A preprocessing stage. arXiv preprint arXiv:1503.06462.
• Bergstra, J., and Bengio, Y. (2012). Random search for hyper-parameter optimization. The journal of machine learning research, 13(1), 281-305.
• Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., ... and Duchesnay, É. (2011). Scikit-learn: Machine learning in Python. the Journal of machine Learning research, 12, 2825-2830.
• Cover, T., and Hart, P. (1967). Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1), 21-27.
• Breiman, L., Friedman, J., Olshen, R., and Stone, C. (1984). Classification and regression trees–crc press. Boca Raton, Florida, 685.
• Breiman, L. (2001). Random forests. Machine learning, 45, 5-32.
• Cortes, C., and Vapnik, V. (1995). Support-vector networks. Machine learning, 20, 273-297.
• Chen, T., and Guestrin, C. (2016, August). Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining (pp. 785-794).
• Cenita, J. A. S., Asuncion, P. R. F., and Victoriano, J. M. (2023). Performance Evaluation of Regression Models in Predicting the Cost of Medical Insurance. arXiv preprint arXiv:2304.12605.
• Bansal, M., Goyal, A., and Choudhary, A. (2022). A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning. Decision Analytics Journal, 3, 100071.