Data-Driven
Mobility Analytics

Understand and optimize the performance of your transport system

Mobility Data & API Integration Tools

Integrate heterogeneous data sources on any transport mode into a unified digital mobility model

Data Integration Pipeline

High-Res Geo Tracking

Collect and process high-resolution tracking data

High Spatio-Temporal Resolution

Location is sampled every second with high-resolution geolocation fusing GPS, WiFi and GSM information.

Map-aware Post-Processing

GPS tracks are post-processed using the digital network model to eliminate noise, improve accuracy and add additional attributes.

Automated Categorization and Labeling

Recorded trajectories are automatically classified based on their properties.

Analyze

Build a wide range of descriptive and predictive models on data in space and time.

Route-oriented

Analyze quantities related directly to roads, streets and paths on which people, vehicles or goods travel within the transport system. Determine traffic volumes, speeds or directionality, identify staypoints. Detect trends and identify anomalies in route-related quantities.

Trips-oriented

Analyze mobility patterns of trips, tours and trip chains. Understand from where to where, when and how people or goods move. Calculate and visualize fine-grained origin-destination matrices and break them down according to time, population segment or trip purpose.

Network-oriented

Analyze the properties of the transport system as a whole. Evaluate connectivity of your system, identify gaps or choke points in your network and suggest extensions that optimize selected network-level KPIs.

Visualize & Interact

Create interactive visual reports of data in space and time

Variable Data Types

Visualizes data with spatial and temporal dimensions. Show quantities linked with locations, lines or areas.

Powerful Filters

Filter data based on locations, time windows, vehicle types, service lines, etc.

Variable Level of Detail

Decide what's going to be shown at different zoom level to reduce clutter and increase understandability.

Scope

Our mobility analytics toolkit can be applied to different type of transport

Cycling-4-3

Cycling & Active Mobility

Analyzing cycling related data to understand cycling behavior: from where to where people travel by bike, when they travel bike, which routes they cycle, and which issues they face.

Modernizace tramvajové trati v úseku Koh-i-noor – Kubánské náměstí

Public Transport & MaaS

Analyze planning and operational aspects of public transport systems: evaluate public transport coverage, analyze line utilization, or service punctuality.

Fleet-4_3

Fleet Management

Analyze strategic and operational KPIs on your fleet ops: monitor vehicle routes, speeds and stop locations, detect deviations and anomalies, identify areas for efficiency improvement.

Case Studies

Selected mobility analytics projects delivered to our customers.

Public Transport Ridership

Counting public transport riders from ticket purchase transactions.

Street-level Cycling Intensity

Determining the intensity and directionality of cycling traffic from GPS tracks and static counters.

Public Transport Quality of Service Coverage

Calculating public transport quality of service coverage KPIs and benchmarking against private car.

P+R potential analysis

Quantifying benefits of intermodal combination of public transport with P+R. XXX XXX XXX XXX XXX XXX XXX XXX XXX XXX​ 

Start unlocking the value in your data!

en_USEnglish
cs_CZČeština en_USEnglish

Analysing Public Transport Ridership

For  a public transport authority (PTA) we have calculated ridership statistics from hundreds of GBs of ticket purchase data. Our analysis provided the PTA with accurate information on how many riders of which category use each public transport service at different times. A challenge here was to reliably map purchase transactions from multiple transport operators to the underlying public transport timetables and to build an interactive map-based data visualization that conveyed the insights the PTA needed to plan optimization of the public transport network.

Key technologies used 

  • GTFS/JDF timetable import and modelling
  • data to timetable matching
  • network-centric data visualization

Street-level Cycling Intensity

For the city of Prague, we have calculated the number of cyclists on each segment of the city’s street and cycleway transport network. For each network segment, we’re provided the number of cyclists travelling in both directions at different times. The analysis required mapping millions of kms of cycling GPS tracks to the underlying model of the transport network and counting data extrapolation using data from stationary cycling counters. The result is provided in a form of an interactive visualization that allows the city to use the analytical output for a number of cycling-related policy decisions.

Key technologies used 

  • OpenStreetMap import and cycling network modelling 
  • GPS track to transport network map-matching
  • Non-uniform counting data extrapolation
  • Interactive network-centric data visualization

Public Transport Coverage Analysis

For a public transport authority, we have calculated quality of service coverage metrics and compared them against private car. For each pair of destinations, we have evaluated all available door-to-door public transport connections and evaluated their travel times, frequencies and number of transfers. We have then compared travel times with travel times by individual car to identify origin-destination pairs for which public transport is highly competetive. The analysis served the PTA for optimizing the design of the public transport network.

Key technologies used 

  • GTFS/JDF Timetable import and transport network modelling
  • Door-to-door public transport journey planning
  • Car route planning with real-world travel time data
  • Map-centric interactive data visualization

P+R Potential Analysis

Employing our network-centric analytics tools, we have evaluated the potential for P+R for Prague metropolitan area. For each settlement, we have compared average travel time to the city center between a door-to-door trip with public transport with an intermodal door-to-door trip combining driving to a P+R facility and then taking a public transport from there. The regions with the highest relative travel time savings when employing P+R compared to public transport-only journey are marked as green. The analysis helps to quantify the benefits of building a P+R facilities in different locations around/in Prague.

 

Key technologies used 

  • GTFS/JDF timetable import and transport network modelling
  • Intermodal door-to-door public transport with P+R routing
  • Car routing with real-world travel time data
  • Map-centric interactive data visualization