Data-Driven Mobility: How Simulation is Reshaping Public Transportation Experience
Fujitsu’s traffic simulation system has been incorporated into Maebashi City’s Regional Public Transportation Plan, marking a notable step in the evolution of data-driven urban mobility. Developed under a national transportation digital transformation initiative, the system combines fixed-route and demand-responsive transport modeling—an approach not previously implemented at this scale in Japan. The system’s outputs have been used as supporting evidence for policy decisions, including the expansion of bus routes.
This Data-Driven Mobility development reflects a broader shift in how public services are designed and delivered. Transportation, traditionally viewed as an operational function, is increasingly being reframed as a customer experience domain. Citizens now expect mobility services that are reliable, flexible, and responsive to their needs—expectations shaped by digital-first consumer platforms.
“Experience design is no longer downstream—it is becoming embedded in infrastructure planning itself.”
Evolving Expectations in Mobility Experience
Public transportation systems globally are under pressure to adapt to changing demographics, environmental goals, and evolving user expectations. Aging populations, urbanization, and workforce constraints are creating structural challenges, while sustainability targets are driving the need for more efficient and low-emission systems.
At the same time, the rise of Mobility-as-a-Service (MaaS) platforms has redefined how users interact with transportation. Seamless journey planning, real-time updates, and personalized options are becoming standard expectations. This convergence of digital and physical experiences requires a new approach to service design—one that integrates data, technology, and human behavior.
For CX leaders, the implication is clear: experience design must extend beyond digital touchpoints to encompass entire service ecosystems.
Strategic Positioning Through Digital Twin Technology
Fujitsu’s approach leverages its digital twin capabilities to simulate human and social behavior within transportation systems. By integrating multiple datasets—including census data, mobility patterns, and app-based ridership information—the system creates a virtual representation of real-world conditions.
This aligns with the company’s broader strategy of applying advanced computing and AI to societal challenges. Rather than focusing solely on enterprise IT solutions, Fujitsu is positioning itself within the smart city and public infrastructure space, where long-term, scalable impact can be achieved.
The ability to model both fixed and demand-responsive transport systems is particularly significant. It reflects a shift toward hybrid mobility models that combine predictability with flexibility, addressing diverse user needs while optimizing resource allocation.
“Hybrid mobility models are redefining how cities balance efficiency with personalization.”
How the Technology Works
At the core of the system are several AI-driven components. Artificial population technology generates synthetic datasets that reflect regional demographics and behaviors. A behavioral selection model uses machine learning to replicate how individuals choose transportation modes based on factors such as travel time, cost, and personal circumstances.
These models are integrated into a multi-agent simulation framework, where different transportation modes interact dynamically. This allows planners to evaluate scenarios with a high degree of accuracy, even in the absence of complete real-world data.
The system also provides visualization tools and evaluation metrics, enabling stakeholders to assess the impact of various policy options. This includes metrics related to service levels, cost efficiency, and usage patterns, offering a comprehensive view of potential outcomes.
“Simulation enables organizations to test and refine customer experiences before real-world deployment.”
Implications for Customer Experience
The introduction of such simulation capabilities has direct implications for customer experience. By aligning service design with actual user behavior, transportation systems can become more intuitive and responsive. For example, optimizing routes based on demand patterns can reduce waiting times and improve accessibility for underserved areas.
Demand-responsive transport introduces a level of personalization, allowing services to adapt to individual needs rather than relying solely on fixed schedules. This is particularly important for populations with limited mobility options, such as elderly residents.
Operational efficiency also plays a critical role. The reported reduction in planning and consensus-building time suggests that authorities can implement changes more quickly, improving responsiveness to evolving conditions. Faster decision-making cycles translate into more agile service delivery, which is a key component of positive customer experience.
“Operational efficiency is no longer separate from CX—it is a primary driver of it.”
Broader Industry Implications
The use of AI-driven simulation in transportation planning is indicative of a broader trend toward predictive infrastructure management. As cities become more data-centric, the ability to anticipate and respond to user needs will become a defining characteristic of successful urban systems.
This shift also has competitive implications. Traditional planning approaches, often reliant on manual analysis and external consulting, may struggle to keep pace with automated, data-driven methods. Technology providers that can offer scalable, integrated solutions are likely to play an increasingly central role.
Moreover, the convergence of transportation modes into unified platforms suggests a move toward ecosystem-based models, where collaboration between public and private stakeholders becomes essential.
“Data-backed decision-making is emerging as a foundation for trust in public services.”
Looking Ahead
Fujitsu’s plans to commercialize the system as a service indicate a broader ambition to standardize this approach across regions. As the technology evolves—incorporating more diverse data sources and refining predictive capabilities—it could become a foundational tool in urban planning and smart city initiatives.
For CX leaders, the key takeaway is the growing importance of simulation and predictive analytics in experience design. Whether in public transportation or other sectors, the ability to model and optimize customer journeys before implementation represents a significant advancement.
This development also signals a deeper transformation: the boundaries between operational systems and customer experience are dissolving. Infrastructure decisions are increasingly being evaluated through the lens of user impact, and data is becoming the bridge between the two.
KEY TAKEAWAYS
- AI-driven simulation is redefining public transportation as a CX discipline
Planning decisions are increasingly guided by customer behavior insights rather than static models. - Digital twin technology enables predictive experience design
Organizations can simulate and optimize services before deployment, reducing risk and improving outcomes. - Hybrid transport models enhance flexibility and personalization
Combining fixed and demand-responsive systems allows for more inclusive and adaptive mobility solutions. - Operational agility directly improves customer experience
Faster planning cycles and data-driven consensus-building enable quicker, more responsive service improvements. - Trust in public services is strengthened through transparency
Evidence-based decision-making helps build confidence among citizens and stakeholders.
