AI-Driven Big Data Analytics for IoT-Enabled Smart City Decision Support Systems: The Nigerian Experience

Smart cities increasingly depend on Internet of Things (IoT) infrastructures, Artificial Intelligence (AI), and big data analytics to support intelligent urban governance and evidence-based decision-making. In developing economies such as Nigeria, however, empirical evaluations of how these technologies translate into operational decision support systems (DSS) remain limited. This study investigates the role of AI-driven big data analytics in IoT-enabled smart city DSS within Nigeria by integrating national digital infrastructure indicators with evidence from smart city initiatives in Lagos, Gwagwalada, and Abaji. This study combines documentary analysis with secondary quantitative and qualitative data to evaluate analytics maturity, governance responsiveness, operational outcomes, and institutional readiness. Findings reveal that Nigeria possesses growing digital and data-generation capacity driven by expanding broadband penetration, mobile connectivity, and urban digitization. However, most smart city deployments remain fragmented and concentrated at descriptive analytics levels, with predictive and prescriptive DSS capabilities emerging only in environments with stronger governance coordination and integrated IoT infrastructure. Key barriers include unreliable power supply, fragmented governance structures, limited interoperability, cybersecurity concerns, inadequate funding, and shortages in technical expertise. The study proposes a scalable AI-driven DSS framework tailored to developing urban contexts and recommends strategic pathways including integrated urban governance, national interoperability standards, sustainable digital infrastructure, and localized innovation ecosystems. The paper contributes empirically grounded insights to the growing literature on smart cities, urban informatics, and AI-enabled governance in emerging economies.

Smart Cities, Internet of Things, Artificial Intelligence, Big Data Analytics, Decision Support Systems

1. Adebayo, T. S., Ogunleye, O. S., & Adeyemi, A. O. (2022). Internet of Things and smart city development in emerging economies. Smart Cities, 5(3), 812–828. https://doi.org/10.3390/smartcities5030042 [Google Scholar] [Crossref]

2. Abdulrahman, L., Musa, M., & Salami, Y. (2024). Artificial intelligence applications in urban governance: Evidence from African cities. Sustainable Cities and Society, 103, 105189. https://doi.org/10.1016/j.scs.2024.105189 [Google Scholar] [Crossref]

3. Akanmu, A. A., & Lawal, A. I. (2022). Data governance challenges in AI-enabled smart cities in developing countries. Cities, 126, 103696. https://doi.org/10.1016/j.cities.2022.103696 [Google Scholar] [Crossref]

4. DataReportal. (2025). Digital 2025: Nigeria. [Google Scholar] [Crossref]

5. Nigerian Communications Commission. (2024). Subscriber statistics and data usage reports. https://ncc.gov.ng/market-data-reports/subscriber-statistics [Google Scholar] [Crossref]

6. Ojo, A., Popoola, S., & Adebisi, B. (2023). Public perception of artificial intelligence for smart city development in Lagos State. Future of Cities and Environment, 9(1), 1–12. [Google Scholar] [Crossref]

7. United Nations. (2024). World urbanization prospects. [Google Scholar] [Crossref]

8. DataReportal (2025) Internet use in Nigeria in 2025. https://datareportal.com/reports/digital-2025-nigeria [Google Scholar] [Crossref]

9. Urban Population Share (2025) Unite Nation. https://population.un.org/dataportal/home?df=de82e89a-4ee1-4316-ab27-67f28ccab88e [Google Scholar] [Crossref]

• What the Desert Fathers Teach Data Scientists: Ancient Ascetic Principles for Ethical Machine-Learning Practice
• Comparative Analysis of Some Machine Learning Algorithms for the Classification of Ransomware
• Comparative Performance Analysis of Some Priority Queue Variants in Dijkstra’s Algorithm
• Transfer Learning in Detecting E-Assessment Malpractice from a Proctored Video Recordings.
• Dual-Modal Detection of Parkinson’s Disease: A Clinical Framework and Deep Learning Approach Using NeuroParkNet