Telematics service detection and action messaging based on machine learning for assisting car sharing platform

A non-transitory computer readable medium containing program instructions that when executed, cause a computer system to:

• train, by one or more processors, a plurality of artificial neural network models by analyzing historical data, wherein each model is trained to generate respective action values for actions corresponding to respective vehicle imperative types, at least one of the plurality of artificial neural network models trained to generate action values for actions corresponding to a non-relocation vehicle imperative type;
• analyze, by the one or more processors, a first data set to determine one or more vehicle imperatives, each comprising one or more respective actions;
• and
• generate, by the one or more processors, a respective action value for each of the respective actions corresponding to the determined one or more vehicle imperatives by analyzing each of the respective actions using a respective one of the plurality of trained artificial neural network models according to a vehicle imperative type associated with each of the one or more respective actions.

A computing system for causing a user of a car sharing platform to perform service or relocation actions with respect to a vehicle, comprising:

• one or more processors;
• and
• one or more memories having stored thereon computer-executable instructions that, when executed by the one or more processors, cause the computing system to:
• train, by the one or more processors, a plurality of artificial neural network models by analyzing historical data, wherein each model is trained to generate respective action values for actions corresponding to respective vehicle imperative types, at least one of the plurality of artificial neural network models trained to generate action values for actions corresponding to a non-relocation vehicle imperative type;
• analyze, by the one or more processors, a first data set to determine one or more vehicle imperatives, each comprising one or more respective actions;
• and
• generate, by the one or more processors, a respective action value for each of the respective actions corresponding to the determined one or more vehicle imperatives by analyzing each of the respective actions using a respective one of the plurality of trained artificial neural network models according to a vehicle imperative type associated with each of the one or more respective actions.