We have built our own proprietary model for predicting and calculating drive times.
The model does not use live traffic data, but instead are built to model congestion levels at the specific time of the day - e.g driving speeds will be slower at 9am than they will be at 1pm, or at 1am.
The model itself takes a range of data sets such as OpenStreetMap and country-specific data, and then constructs speed profiles based around road types, the surrounding area, and features of the road itself.
These speed profiles are then benchmarked on test maps, fine-tuned, and then set live.
Once live, the models are regularly re-tested and updated.
Where a driving route starts or ends away from a road, we apply a time penalty based on how long it would take to walk to the road (see more details here).
Process in detail
The map is broken down into urban and rural areas at a detailed local level, using data such as municipality limit shapes and speed limits
The final areas are: Rural, Village, Town, Urban, City, Extra Urban, Dense Urban
All roads are tagged with a road type, e.g residential, tertiary, trunk, motorway, etc.
A library of representative trip samples is built
Statistical modelling techniques are applied to build speed profiles for all combinations of road types and area, including the density of different connecting road types
A test map is built
The speed profiles are applied to real-world routes, taking into account map features such as traffic lights and zebra crossings, and peak and off-peak times
Where appropriate, driving routes are book-ended with walking to represent how people actually travel, rather than simply ‘snapping’ to or from the nearest road
Drive time predictions are tested extensively against a number of real-world routes and actual journeys
The results of these tests are used to fine-tune the algorithm and speed profiles
The model goes live, and is then regularly tested and benchmarked, and updated where appropriate