Personalized ride experience based on real-time signals

A computing system comprising:

• one or more processors and one or more computer-readable non-transitory storage media coupled to one or more of the processors, the one or more computer-readable non-transitory storage media comprising instructions operable when executed by one or more of the processors to cause the computing system to perform operations comprising:
• receiving data associated with sensory output from one or more sensors associated with a vehicle, the sensory output being associated with at least a ride requestor while the ride requestor is at least partially within a passenger compartment of the vehicle, wherein the vehicle is matched with the ride requestor for transporting the ride requestor to a request location;
• extracting features from the received data according to a machine-learning model, wherein the machine-learning model is trained using a set of training data, wherein each training data in the set of training data is associated with sensory output relating to one or more predetermined event types;
• generating, using the machine-learning model and the features extracted from the received data, a score representing a likelihood that the received data is indicative of a first event type selected from the one or more predetermined event types;
• and
• generating an alert based a determination that the score satisfies a predetermined criterion.

One or more computer-readable non-transitory storage media embodying software that is operable when executed to cause one or more processors to perform operations comprising:

• receiving data associated with sensory output from one or more sensors associated with a vehicle, the sensory output being associated with at least a ride requestor while the ride requestor is at least partially within a passenger compartment of the vehicle, wherein the vehicle is matched with the ride requestor for transporting the ride requestor to a request location;
• extracting features from the received data according to a machine-learning model, wherein the machine-learning model is trained using a set of training data, wherein each training data in the set of training data is associated with sensory output relating to one or more predetermined event types;
• generating, using the machine-learning model and the features extracted from the received data, a score representing a likelihood that the received data is indicative of a first event type selected from the one or more predetermined event types;
• and
• generating an alert based a determination that the score satisfies a predetermined criterion.