Parking is problematic:
£30 BnAnnual cost of parking searches
in the UK for municipalities |
10%Of revenue spent on
maintenance cost of sensors |
30%Portion of congestion in big cities created by drivers searching for parking
|
Boetho advanced data analysis services
provide solutions to parking managers and councils
by harnessing the power of Machine Learning
to leverage readily available payment data
to predict demand and optimise utilisation.
provide solutions to parking managers and councils
by harnessing the power of Machine Learning
to leverage readily available payment data
to predict demand and optimise utilisation.
Boetho,
One Common Solution
to congestion and parking utilisation
A Complete Set of ServicesOne Week ahead prediction
Boetho’s Bayesian Machine Learning algorithm predicts future parking occupancy based on current payment data. Recognizes patterns, trends and seasonality.
smart Pricing
Boetho’s smart pricing formula seamlessly updates parking fees according to predicted occupancy rates on a weekly basis. Matching prices to demand results in higher revenues and lower average prices for parking users.
Optimal allocation
In large scale applications, our Optimal Allocation algorithm ensures that a global optimal use of the parking resources is reached.
Booking system optimisation
Parking owners can optimize the revenue stream from their booking systems by matching prices with future demand, as well as minimize the time needed to keep a spot reserved.
|
Seamless Implementation |
The Optimal Solution
For Everybody
For Parking OwnersSustainable revenue growth secured through higher average rates of parking occupancy and increased per car profitability.
> 10%Potential revenue increase
|
For DriversReduction in number of hours wasted on parking searches. Parking prices adapt in advance to keep an optimised occupancy rate. This way drivers will pay a fair price determined by supply and demand.
67 hYearly time gain per driver
|
For SocietyReduced pollution from traffic congestion, costs of infrastructure maintenance and illegal parking.
> 30%Lower CO2 emissions
|
Powered By
State Of The Art Technologies
Predictive AlgorithmWhen it comes to collecting and analysing parking data, the current focus is on providing drivers and parking owners with live data. Unfortunately, live data is expensive to collect, as it requires the deployment of sensors and cameras, which pose both a high cost of implementation and maintenance.
At the same time, live data is also ineffective. For instance, a parking owner cannot chose its pricing strategy based on live data, as the fees need to be given in advance to the drivers. Both drivers and parking owners need to know future parking occupancies to adapt their behaviour and policies, resulting in a more efficient use of parking resources. To answer these problems, Boetho's algorithm uses the readily available payment data to forecast with high accuracy the occupancy rates for the week ahead. |
Considering Drivers' ReactionWhen using a predictive algorithm it is important to take into account that individuals will react to the forecast. In our case, drivers will change their behaviour if future parking occupancies are disclosed to them, or if parking owners implement new pricing strategies. Thus, the algorithms used for the predictions must be adaptive.
At the same time, the optimal allocation of the resources of a parking network requires more than the communication of the predictions. Drivers react similarly to the new information, thus shifting the problem without solving it. At Boetho, we have developed an algorithm that solves the allocation problem on a large scale, taking into account driver reactions. |
Dynamic Pricing in the News
Optimal Parking for Public Parking Garages
"Cities can better manage off-street parking by prioritizing occupancy and availability, not just revenue." By G. Pierce, H. Willson, D. Shoup |
Dynamic Pricing
"It has been studied, applied, reviewed and critiqued – but what is it exactly and why would councils consider using it?" By Parking Network |
Optimum Parking Management
"Integrating digital technologies into dynamic parking management" By Indigo |
References.
[1] Navigant Research (2017). Transportation Forecast: Light Duty Vehicles
[2] Arnott, R., Rave, T., and Schöb, R. (2005). Alleviating Urban Traffic Congestion. MIT Press
[3] Soup, D. (2007). Cruising for parking
[4] Cookson, G. (2017). Smart Parking – A Silver Bullet for Parking Pain. INRIX Research
[5] Transportation Alternatives (2007). No Vacancy: Park slope’s parking problem and how to fix it
[6] National Cancer Intelligent Network (2011). The effect of rurality on cancer incidence and mortality
[7] Caliskan, M., Graupner, D. and Mauve, M. (2006). Decentralized Discovery Of Free Parking Places
[8] Urban Transportation Task Force (2012). The High Cost of Congestion in Canadian Cities
[1] Navigant Research (2017). Transportation Forecast: Light Duty Vehicles
[2] Arnott, R., Rave, T., and Schöb, R. (2005). Alleviating Urban Traffic Congestion. MIT Press
[3] Soup, D. (2007). Cruising for parking
[4] Cookson, G. (2017). Smart Parking – A Silver Bullet for Parking Pain. INRIX Research
[5] Transportation Alternatives (2007). No Vacancy: Park slope’s parking problem and how to fix it
[6] National Cancer Intelligent Network (2011). The effect of rurality on cancer incidence and mortality
[7] Caliskan, M., Graupner, D. and Mauve, M. (2006). Decentralized Discovery Of Free Parking Places
[8] Urban Transportation Task Force (2012). The High Cost of Congestion in Canadian Cities