Revolutionising Urban Mobility with ML and Smart Transport
Synopsis
With a disconnected transport network, our client recognised the pressing need to overhaul its public transportation infrastructure to accommodate a growing population and address increasing congestion issues. They sought a data-driven solution to redesign the metro network that would enhance efficiency, reduce commute times and improve overall mobility within the city.
Our groundbreaking engagement sought to transform urban mobility by employing an innovative approach that integrated customer sensory data with telco network operator data to design intelligent, data-driven transportation networks.
Utilising advanced machine learning algorithms, we meticulously analysed population movement behaviours, offering critical insights into how people navigated one of the largest metropolitan areas in the region. This comprehensive data-driven analysis allowed us to strategically plan the entire metro network, optimising connectivity and accessibility to best serve urban residents.
Client Overview
🔸A leading metropolitan government organisation.
🔸c.5 million daily commuters
🔸Complex zone to zone mapping
🔸3 terabyte of telco network data
Client Problem
“Our pioneering methods in smart transport and transport network design not only enhance commuter experiences but also streamline urban mobility, resulting in smarter, more resilient cities. By focusing on urban mobility, smart transport, and machine learning, we are paving the way for the future of transportation—creating networks that are responsive, efficient, and tailored to the needs of a rapidly changing urban landscape.”
Â
Analytics Delivery
🔸A multidisciplinary approach that combined sensory data from various sources
🔸Leveraging advanced machine learning techniques to extract valuable insights into population movement behaviours.
🔸Analysing historical data and real-time information to identify patterns and trends in commuter travel
🔸Optimise the design of the newly planned metro system to mitigate cost and maximise commuter accessiblity and urban mobilityÂ
The Challenge
The client faced several challenges in planning the metro network effectively.
⦿  Lack of comprehensive data on population movement patterns within the city.
⦿  Difficulty in understanding the dynamic nature of urban mobility and predicting future trends.
⦿  Limited insights into optimal routes and station locations to maximise accessibility and ridership.
⦿  Pressure to minimise costs while maximising the impact of infrastructure investments.Â
⦿  Integrating disparate datasets from different sources and ensuring data quality and accuracy.
⦿  Additionally, processing and analysing large volumes of complex data required robust computational infrastructure and expertise in advanced analytics techniques.
Trusted Data Approach
⦿ To address the challenge of data quality and reliability, we implemented a rigorous data validation and cleansing process.
⦿ We collaborated closely with the telco network operator to ensure the integrity of the data and mitigate potential biases or inaccuracies.
⦿ Establishing data governance protocols and leveraging industry best practices, we ensured that the analytical insights derived from the data were reliable and actionable.Â
⦿ Leveraging advanced machine learning and data analytics, we were able to model and recommend:
   –  An optimal routing network for the city-wide metro system
   –  Ideal geo-location points for metro stops to accommodate population movements and maximise ridership.
OUR IMPACT
Million Budget Savings
%
Population Coverage
%