Driving Intelligence: How AI is Powering Nigeria’s Transport Sector, One Fleet at a Time

By Dereck jamilu

As Nigeria’s transport sector confronts growing inefficiencies, aging vehicles, and a demanding supply chain, a quiet revolution is taking shape—powered by artificial intelligence and predictive analytics. Across major cities like Lagos, Port Harcourt, and Abuja, technology-driven logistics companies are embedding AI into the very heart of their fleet-management systems. The trend has opened new frontiers in what has historically been a risk-prone, analog-dominated sector. Among the professionals leading this transformation is Foluke Ekundayo, a Lagos-based enterprise IT expert who has helped one of Nigeria’s regional logistics providers reduce fraud, improve safety, and integrate predictive technology into their transport systems.

“It’s not just about tracking vehicles anymore,” Ekundayo tells Thisday. “It’s about understanding the behavioral patterns behind how assets are used—and optimizing for that.” With nearly a decade of experience in enterprise IT and a robust background in industrial systems, Ekundayo has emerged as one of Nigeria’s key voices in logistics intelligence and transport-system digitalization.

Ekundayo’s journey into applied AI and transport intelligence began at the University of Ghana, where she graduated with a Bachelor’s degree in Computer Science and Management (Hons) in 2014. The program merged the theoretical depth of computing with core business and organizational strategy—an interdisciplinary focus that would shape her early technical approach. Shortly after graduation, she returned to Nigeria and joined Nestlé Nigeria Plc in 2010 as an IT Support Specialist—a role that, despite its factory-floor focus, offered crucial exposure to enterprise system stability, hardware resilience, and uptime-critical environments. At Nestlé, she deployed and maintained over 80 production workstations across regional locations, achieved zero data packet loss during Q3 2012 through early fault-detection protocols, and led a network-wide PC-optimization initiative that reduced system downtime by 20 percent, improving factory workflow efficiency. “Working in a manufacturing environment taught me something that never left me—systems need to predict failure, not just respond to it,” she says.

In 2014, Ekundayo joined Fleet Rentals & Logistics Limited, one of Nigeria’s growing transport companies serving major commercial hubs, as Regional IS/IT Manager overseeing digital infrastructure across multiple locations. She saw an opportunity to apply advanced analytics and machine-learning tools to persistent logistics issues—driver inefficiency, fraudulent claims, unplanned maintenance, and late deliveries. She led the design and deployment of a fully integrated AI-based telematics and fleet-monitoring system—an innovation rare in Nigeria’s transport industry at the time. Key components included telematics with ML-driven driver-behavior scoring that classified incidents like harsh braking, fatigue, and speeding; predictive-maintenance models that flagged potential vehicle failures before they occurred; anomaly detection for expense tracking that spotted suspicious patterns in fuel purchases, spare-part use, and mileage claims; and route-optimization algorithms that replaced fixed delivery schedules with real-time dynamic routing based on traffic and vehicle load.

By 2018, the system had become business-critical, delivering a 25 percent reduction in fraud-related financial losses, a 40 percent decline in vehicle accidents thanks to behavior-based driver alerts and route-risk predictions, a 15 percent improvement in delivery accuracy and punctuality compared with pre-2015 baselines, and cost savings exceeding ₦60 million in maintenance and delivery efficiency over four years. “AI doesn’t replace human decision-making,” Ekundayo says. “It enhances it—by turning raw operational data into actionable intelligence.” Her leadership fostered an internal culture shift, with drivers, dispatchers, and supervisors relying on dashboards, alerts, and maintenance predictions as part of daily routines.

Ekundayo championed continuous experimentation and feedback loops, collaborating with developers and IT staff to roll out internal training dashboards that visualized driver performance and predicted breakdown risk by vehicle class. This strategy not only improved safety but also elevated worker engagement, as staff could view individual scores and receive corrective suggestions via an in-house app. “We weren’t just installing software,” Ekundayo notes. “We were building an intelligent assistant that worked beside each team member.” The human-centered machine-learning focus proved game-changing, earning her internal commendations and external interest from regional transport experts looking to replicate the approach.

Before her logistics achievements, Ekundayo made her mark in industrial IT systems at Nestlé Nigeria’s manufacturing units between 2010 and 2014. She managed factory asset inventories across multiple plant zones, coordinated printer, router, and server setups for regional logistics offices, reduced factory-wide troubleshooting cycles through pre-failure flagging and user-escalation tracking, and led firmware updates ensuring consistency across devices in more than five Nigerian states. This grounding in mission-critical environments underpinned her later success in high-responsibility fleet-system transformations.

While Nigeria’s transport and logistics sector remains male-dominated, Ekundayo’s rise signals a shift in gender expectations within technical management. Leading high-impact IT operations and deploying ML-powered solutions at scale, she has become an inspiration for female professionals across West Africa. “The system doesn’t automatically expect you to lead,” she concedes. “But when you bring results that save money, reduce risk, and improve service—gender takes a back seat.” Her success highlights the growing pipeline of female technologists building infrastructure-grade systems—not just apps or platforms—in Nigeria’s private sector.

As of mid-2019, Ekundayo held ITIL Foundation credentials for enterprise IT governance and infrastructure best practices, had completed Cisco Certified Network Associate coursework, and possessed in-house certifications in fleet tracking, application support, and Microsoft systems. She was also preparing to enroll in specialized data-analytics and AI-certification programs to formalize her expanding command of Python-based machine-learning models used in logistics.

Her approach remains pragmatic, localized, and impact-oriented. She prioritizes cost-effective deployments aligned with Nigeria’s unique transport infrastructure—where downtime is expensive, fuel fraud common, and real-time insights often inaccessible. “We couldn’t wait for Western platforms to be adapted to us. We had to build around our reality, our risks, and our resources,” Ekundayo explains. Her models account for regional variability, driver-behavior patterns in congested urban zones, and inconsistencies in power and internet connectivity—factors rarely considered in off-the-shelf fleet solutions.

As Nigeria considers smart-transport policies and digital asset tracking in the public sector, experts cite Ekundayo’s work as a proof of concept. Transportation policy adviser Dr. Abubakar Idris argues that if such systems work in private firms with low budgets, multiple branches, and tight timelines, public-sector deployments are feasible once local professionals are empowered. Many of the solutions she introduced—predictive routing, usage-based risk scoring, and asset-lifecycle modeling—could be directly adapted to public-transport maintenance scheduling, municipal waste-collection routing, and emergency-fleet dispatch optimization.

In Africa’s fast-evolving technology landscape, it is often the silent optimizers—those who build operational systems rather than headline-grabbing apps—who create the most sustainable change. By 2019, Foluke Ekundayo had not only transformed a Nigerian logistics company from within; she had shown how indigenous AI deployment, grounded in operational fluency and business value, can thrive in real-world conditions. In doing so, she set a new benchmark for what’s possible when systems thinking, data discipline, and fearless experimentation intersect. “We didn’t wait for Silicon Valley to solve our problems,” she says with a smile. “We solved them ourselves—with Python, with persistence, and with purpose.”