Route selection using machine-learned safety model

A system comprising:

• at least one hardware processor;
• and
• a machine storage medium embodying a set of instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform operations comprising:
• obtaining accident data and feature data for each route of a plurality of historical routes that have been communicated electronically as navigation guidance, the accident data indicating whether a vehicular accident occurred in association with the historical route, the feature data being based on maneuvers comprising a maneuver connecting each edge that forms the navigational guidance of the historical route and comprising at least one maneuver statistic from maneuver statistics calculated based on the maneuvers of the historical route, the maneuver statistics comprising one or more of a total number of the maneuvers of the historical route, a maneuver distance statistic based on distances of the maneuvers of the historical route, a maneuver duration statistic based on durations associated with the maneuver of the historical route, a maneuver speed statistic based on speeds associated with the maneuvers of the historical route, a heading change statistic based on degrees of heading changes associated with the maneuvers of the historical route, or a compound maneuver statistic based on a total number of compound maneuvers of the historical route;
• training a safety risk model using the accident data and the feature data of the plurality of historical routes as training data in a machine learning process;
• receiving a request for a route from a starting geographic location to a destination geographic location;
• generating a plurality of candidate routes from the starting geographic location to the destination geographic location;
• selecting a candidate route of the plurality of candidate routes based on a safety score for the selected candidate route that was generated using the trained safety risk model;
• and
• causing the selected candidate route to be displayed within a user interface on a computing device of a transportation provider for navigation to a given destination.

A machine storage medium embodying a set of instructions that, when executed by at least one hardware processor, cause the processor to perform operations comprising:

• obtaining accident data and feature data for each route of a plurality of historical routes that have been communicated electronically as navigation guidance, the accident data indicating whether a vehicular accident occurred in association with the historical route, the feature data being based on maneuvers comprising a maneuver connecting each edge that forms the navigational guidance of the historical route and comprising at least one maneuver statistic from maneuver statistics calculated based on the maneuvers of the historical route, the maneuver statistics comprising one or more of a total number of the maneuvers of the historical route, a maneuver distance statistic based on distances of the maneuvers of the historical route, a maneuver duration statistic based on durations associated with the maneuver of the historical route, a maneuver speed statistic based on speeds associated with the maneuvers of the historical route, a heading change statistic based on degrees of heading changes associated with the maneuvers of the historical route, or a compound maneuver statistic based on a total number of compound maneuvers of the historical route;
• training a safety risk model using the accident data and the feature data of the plurality of historical routes as training data in a machine learning process;
• receiving a request for a route from a starting geographic location to a destination geographic location;
• generating a plurality of candidate routes from the starting geographic location to the destination geographic location;
• selecting a candidate route of the plurality of candidate routes based on a safety score for the selected candidate route that was generated using the trained safety risk model;
• and
• causing the selected candidate route to be displayed within a user interface on a computing device of a transportation provider for navigation to a given destination.