Optimizing data and voice service delivery for mobile phones based on clients' demand and location using affinity propagation machine learning

Emmanuel C. Ukekwe; Adaora A. Obayi; Akpa  Johnson; Daniel A.  Musa; Jonathan C. Agbo

doi:10.46481/jnsps.2025.2109

Authors

Emmanuel C. Ukekwe
[email protected]
Department of Computer Science, University of Nigeria, Nsukka, Nigeria
Adaora A. Obayi Department of Computer Science, University of Nigeria, Nsukka, Nigeria
Akpa Johnson Department of Computer Science, Prince Audu Abubakar University, Anyigba, Nigeria
Daniel A. Musa Department of Computer Science, Prince Audu Abubakar University, Anyigba, Nigeria
Jonathan C. Agbo Department of Computer Science, University of Nigeria, Nsukka, Nigeria

Keywords:

Telecommunication, Clustering, Machine-learning, Subscription, Tariff plans

Abstract

Network service requests for voice and Internet may differ across locations. Network service providers are encouraged to conduct a quarterly check to identify the service plan that is mostly sought for in a particular area of coverage to improve the quality of service through promotions, advertisements and awareness talks. In this work, a model that identifies and recommends the location service plan for network providers is proffered. The 3-task model extracts data as quarterly averages on voice and Internet subscriptions it goes ahead to cluster the extracted data using affinity propagation machine learning and classifies the clusters into linguistic variables using the mean of the respective clusters. Using a dataset obtained from the Nigerian Bureau of Statistics on mobile telecommunication on the four major network operators of Mtn, Airtel, Glo and 9Moile for three quarters in 2021, the model was able to identify states with heavy as well as low subscription rates (voice and Internet) across the country. The more urbanized states preferred internet subscription over voice calls thereby revealing the weakness and strength of each network provider across the states. Mtn had the best Davies-Bouldin Index performance measure of 0.26, Glo had the best silhouette score of 0.66 while 9Mobile had the best Calinski-Harabasz Index metric score of 805.30.

Dimensions

REFERENCES

[1] R. Hossain, R. Hasan & M. Sharmin, “A short review on the history of mobile phones”, Journal of Android, IOS Development and Testing 7 (2022) 33. https://www.researchgate.net/publication/362033694_A_Short_Review_on_the_History of_Mobile_Phones.

[2] D. J. Micah, “The advent of mobile telecommunications services in Nigeria: Exploring a decade of social change (2001–2011)“ In: Baikady, R., Sajid, S., Nadesan, V., Przeperski, J., Islam, M.R., Gao, J. (eds) The Palgrave Handbook of Global Social Change. Palgrave Macmillan, Cham. California, U.S.A, 2022, pp. 1–20. https://doi.org/10.1007/978-3-030-87624-1_283-1.

[3] K.S. Sridhar & V. Sridhar, “The effect of telecommuting on suburbanization: Empirical evidence”, Journal of Regional Anal. Policy 33 (2003) 1. https://www.researchgate.net/publication/228923346_The_effect_of_telecommuting_on_ suburbanization_Empirical_evidence.

[4] A. Harris & M. Cooper, “Mobile phones: Impacts, challenges, and predictions”, Hum Behav & Emerg Tech. 2019 (2019) 15. https://doi.org/10.1002/hbe2.112.

[5] S. Katsumata, T. Ichikohji, S. Nakano, S. Yamaguchi & F. Ikuine, “Changes in the use of mobile devices during the crisis: Immediate response to the COVID-19 pandemic”, Computers in Human Behavior Reports 5 (2022) 100168. https://doi.org/10.1016/j.chbr.2022.100168.

[6] S. A. Odunlami, M. A. Abioro & F. O. Okeowo, “Promotional mix and customer patronage: a study of telecom subscribers in Lagos and Ogun States, Nigeria”, Covenant Journal of Business & Social Sciences (CJBSS) 11 (2020) 80. http://journals.covenantuniversity.edu.ng/index.php/cjbss.

[7] E. G. Igiba, M. I. Abubakar & D.Z. Salihu, “Effect of technology adoption on service delivery in the telecommunication industry in Nigeria”, International Journal of Management Sciences 10 (2023) 123. https://arcnjournals.org/images/27751456791018.pdf.

[8] M. H. Hassan, “Applications of machine learning in mobile networking”, Journal of Smart Internet of Things (JSIoT) 2023 (2023) 23. https://doi.org/10.2478/slot-2023-0003.

[9] B. Litwin, K. Elleithy & L. Almazaydeh, “Machine learning applications to mobile network performance modeling”, Journal of Theoretical and Applied Information Technology 99 (2021) 1815. http://www.jatit.org/volumes/Vol99No8/10Vol99No8.pdf.

[10] C. Zhang, P. Patras & H. Haddadi, “Deep learning in mobile and wireless networking: A survey”, IEEE Communications Surveys & Tutorials 21 (2019) 1. https://doi.org/10.1109/COMST.2019.2904897.

[11] H. Wu, X. Li & Y. Deng, “Deep learning-driven wireless communication for edge- cloud computing: opportunities and challenges”, Journal of Cloud Computing: Advances, Systems and Applications 9 (2020) 2. https://doi.org/10.1186/s13677-020-00168-9

[12] X. Liu & Z. Li, “Dynamic multiple access based on deep reinforcement learning for Internet of Things”, Computer Communications 210 (2023) 331. https://doi.org/10.1016/j.comcom.2023.08.012.

[13] O. A. Toluwanimi & J. R. Olayinka, “Optimization opportunities in nigeria telecoms terrestrial network - A Review”, EJERS, European Journal of Engineering Research and Science 3 (2018) 70. http://dx.doi.org/10.24018/ejers.2018.3.10.941.

[14] A. O. Aliyu, U. I. Idris & P. E. Omaku, “Optimizing internet subscriptions for Mtn And Glo data plans”, Global Journal of Pure and Applied Sciences 30 (2024) 221. https://dx.doi.org/10.4314/gjpas.v30i2.11.

[15] N. A. Ndife , A. U. Okolibe, E. O. Ifesinachi, D. K. Nnanna, “Evaluation and optimization of quality of service (QoS) of mobile cellular networks in Nigeria”, International Journal of Information and Communication Technology Research 3 (2013) 277. https://api.semanticscholar.org/CorpusID:67838539.

[16] C. K. Agubor, N. C. Chukwuchekwa, E. E. Atimati, U. C. Iwuchukwu & G. C. Ononiwu, “Network performance and quality of service evaluation of gsm providers in Nigeria: A case study of Lagos State”, International Journal Of Engineering Sciences & Research Technology (IJESRT) 3 (2016) 256. https://dx.doi.org/10.5281/zenodo.154167.

[17] C. N. Okwurume, “Optimizing telecommunication services quality delivery: The impact of competitive intelligence systems”, ARCN International Journal of Advanced Academic and Educational Research 14 (2024) 1. https://www.arcnjournals.org/images/27261-452237-014111.pdf.

[18] D. Bolanos-Martinez, M. Bermudez-Edo & J. L. Garrido, Clustering˜ pipeline for vehicle behavior in smart villages”, Information Fusion 104 (2024) 102164. https://doi.org/10.1016/j.inffus.2023.102164.

[19] T. Koshimizu, S. Gengtiani, H. Wang, P. Zhenni, L. Jiang & S. Shigeru, “Multi- dimensional affinity propagation clustering applying a machine learning in 5g- cellular V2X”, IEEE Access 8 (2020) 1. https://doi.org/10.1109/ACCESS.2020.2994132.

[20] J. Wang, G. Yu, K. Wang A. Kumar & L.Se-Jung, “An affinity propagation-based self-adaptive clustering method for wireless sensor networks”, sensors 19 (2019) 2579. https://doi.org/10.3390/s19112579.

[21] B. Hassanabadi, C. Shea, L. Zhang & S. Valaee, “Clustering in vehicular ad hoc networks using affinity propagation”, Ad Hoc networks 13 (2014) 535. https://doi.org/10.1016/j.adhoc.2013.10.005.

[22] NBS, “Telecoms data: active voice and internet per state, porting and tariff information”, (2021). [Online] https://nigerianstat.gov.ng/elibrary/read/1241133.

[23] MTN cheapest tariff plans in Nigeria for data & calls (2024). [Online]. https://www.networkpalava.com.ng/2019/06/ mtn-cheapest-tariff-plans-code.html.

[24] MTN, “Data plans” (2024). [Online]. https://www.mtn.ng/.

[25] Airtel, “Voice & Data”, (2024). [Online]. https://www.airtel.com.ng/.

[26] Glo, “Tarrif Plans”, (2024). [Online] https://www.gloworld.com/ng/personal/voice/tarrif-plans

[27] 9mobile, “Packages & plans”, (2024). [online]. https://9mobile.com.ng/packages-plans.

[28] The Guardian, “Why 3G technology remains dominant in Nigeria”, (2020). [Online]. https://guardian.ng/technology/why-3g-technology-remains-dominant-in-nigeria/.

[29] Statista, “3G/4G mobile broadband penetration rate in Nigeria 20172022”, (2022). [Online]. https://www.statista.com/statistics/549567/mobile-lte-subscriptions-in-nigeria/.

[30] Nperf, “3G / 4G / 5G coverage map, Nigeria”, (2024). https://www.nperf.com/en/map/NG/-/-/signal/?ll=9.117314075024407&lg=8.670000000000005&zoom=6

[31] Q. Iqbal, A. Mujtaba, A. Sikandar, K. Shumaila, A. M. Mogeeb, A. Ahmed, K. Hizbullah, A. Mahmood, “Affinity Propagation-Based Hybrid Personalized Recommender System”, Complexity 2022 (2022) 1. https://doi.org/10.1155/2022/6958596.

[32] R. Rina, B.M. Achmad, J. Asep & S.A. Adang, “A Preference Model on Adaptive Affinity Propagation”, International Journal of Electrical and Computer Engineering (IJECE) 8 (2018) 1805. https://doi.org/10.11591/ijece.v8i3.pp1805-1813.

[33] G. Haimiao, W. Liguo, P. Haizhu,Z. Yuexia, Z. Xiaoyu & L. Moqi, “Affinity propagation based on structural similarity index and local outlier factor for hyperspectral image clustering”, Remote Sens 14 (2022) 1195. https://doi.org/10.3390/rs14051195.

[34] J. P. Olumuyiwa, S. F. Gerard, J. O. Agbaje & K. Oshinubi, “An empirical study on anomaly detection using density-based and representative-based clustering algorithms”, Journal of the Nigerian Society of Physical Sciences 5 (2023) 1364. https://doi.org/10.46481/jnsps.2023.1364.