Yango Group’s AI routing technology saved users 5 million hours in 2025

Yango Group, global tech company digitalising urban services, today announced that its advanced AI-powered routing technologies saved urban commuters more than 5 million hours in 2025 across 20+ cities of its presence — the equivalent of 600 years of human time returned to communities. The findings, based on an analysis of millions of Yango Ride trips in 2025, prove that intelligent routing delivers tangible quality-of-life improvements at scale, establishing AI-driven mobility as critical infrastructure for modern cities. Yango’s routing system leverages a sophisticated combination of machine learning models, real-time traffic data, and historical analysis to optimize every journey, processing multiple data streams simultaneously to calculate the most efficient route in milliseconds.

“Five million hours saved isn’t a tech metric — it’s proof that AI can solve real urban problems at scale,”said Adeniyi Adebayo, Chief Business Officer of Yango Group. “We’re demonstrating that the next generation of city infrastructure won’t be built with concrete and steel alone, but with data, algorithms, and intelligence embedded into everyday services.” The research compared AI-optimized routes against static shortest paths that ignore live traffic conditions. Results showed significant time savings across varied urban landscapes.

For example, in Zambia , the total annual time saved was almost 300,000 hours while time saved per active passenger on Yango was about an hour and half. In Lima, users reclaimed over 1.1 million hours annually — the largest absolute saving among studied cities. Kinshasa residents saved an average of 6.48% per trip, while Guatemala City commuters experienced the highest efficiency gains at 6.99%.

[paywall]

In Abidjan, the most active riders gained more than 2 hours per year individually. The cumulative effect represents 5 million hours returned to urban economies and communities in a single year. The technology processes information about road characteristics, traffic light patterns, turn complexity, and predictive congestion modeling.

The system’s self-learning architecture continuously improves accuracy by comparing predicted versus actual travel times, creating an evolving feedback loop that adapts to each city’s unique patterns. Beyond time savings, intelligent routing contributes to broader urban sustainability goals.

[/paywall]