The issue of rebalancing is critical to manage a micro-mobility system. A system is never perfectly balanced by itself.
Some areas are primarily departure areas and others are arrival areas.
Many external factors can impact the use of the system and require dynamic changes in the rebalancing strategies (e.g., holidays, weather).
Over time, user behaviors can change, making it necessary to continually re-evaluate these strategies
A more effective rebalancing strategy for an optimized and sustainable shared mobility system
Increase vehicle use rate through high quality service
Reduce your operating costs by optimizing each trip to pick up/drop off a shared vehicle
Automate your fleet dispatching and rebalancing for better service
Modeling of vehicle rentals and returns by station or by zone
Calculation of the optimal number of shared vehicles to relocate per station or per zone for a maximum number of rentals
Automatic optimization of each tour to match the rebalancing strategy (availability of bikes, reduction of kilometers traveled by vans, productivity of the operators etc.)
State-of-the-art technology
Our predictive models calculate user rentals and returns of scooters/bikes, as well as unmet demand up to 24 hours in advance. They are based on multiple data sources processed in real-time by contextual machine learning algorithms:
Real-time station occupancy (number of vehicles and free spaces)
Dynamics of each station over the last few hours
Calendar data (time of day, day of week, day of year, holidays, school holidays)