For the complete documentation index, see llms.txt. This page is also available as Markdown.
Mobility Insights
Learn how to gain insights into user movement and behavior from mobility data.
Introduction to Mobility Insights
Our platform can help you understand how your users move around and travel using different modes of transportation. We can provide details about their mobility patterns, which means we can track how they go from one place to another, whether they use a car, bicycle, train, etc.
Mobility insights are derived from location and sensor data. This data is processed by ML models to identify the transport modes used during a trip from location A to location B.
A single trip may consist of multiple segments for example, biking to a train station, taking the train, and then a bus to the final destination. Each segment includes distance, duration, and additional contextual details, which together form the complete trip overview.
Features Overview
1
Transport Mode Detection
Identifies the mode(s) of transport used during a trip. Multiple modes can be detected within a single journey, see below for a list of our official supported transport modes
Walking
Running
Bicycle
Motorcycle
Car
Bus
Tram
Metro
Train
Idle
2
Modal Split
Aggregates total distance, duration, and number of trips per transport mode. This provides a clear overview of the user’s mobility patterns and insights into their preferred mode of transport
3
Event Timeline
Mobility Insights can detect when a user starts moving and when they become stationary. These events can be captured and made available in your application either in real time or retrieved on demand.
Transport Event
Represents a moment when the user was in movement
Stationary Event
Represents a moment when the user was not in movement or stopped moving
Off The Grid Event
Represents a moment when the users movement status could not be determined due to different reasons:
