System and method for predicting a destination for a vehicle

A non-transitory computer-readable storage medium embodying programmed instructions which, when executed by a processor, are operable for performing a method comprising:

• receiving a trip history for an operator of a vehicle, wherein the trip history includes trip information regarding a plurality of previous trips by an operator of the vehicle;
• generating a data cluster corresponding to each destination in the trip history by extracting a plurality of input features from trip information for each trip in the trip history, wherein the plurality of input features characterize a relationship between the operator of the vehicle and the plurality of previous trips and the plurality of input features for each data cluster includes at least one of the input features characterizes a current location for a newly initiated trip with respect to a destination for each of the plurality of previous trips;
• generating a training dataset based on collecting the data cluster corresponding to each of the destinations in the trip history;
• training a gradient boosted trees model utilizing the training dataset with hyperparameter tuning, wherein the hyperparameter tuning includes applying class weights to each of the plurality of input features based on their respective contribution to destination prediction in the gradient boosted trees model;
• predicting a plurality of possible destinations for the operator of the vehicle with the gradient boosted trees model utilizing an origin location of the operator of the vehicle, a time of day, and a day of the week as input conditions for the gradient boosted trees model;
• displaying a plurality of possible destinations on a display in the vehicle along with a confidence level that each of the plurality of possible destinations is a desired destination;
• and
• providing directions with a navigation system on the vehicle to the desired destination based on a selection by the operator of the vehicle from the plurality of possible destinations on the display.

A vehicle comprising:

• a vehicle body supported by a plurality of road wheels;
• a vehicle navigation system configured to provide directions to a destination;
• and
• a controller in communication with the navigation system and configured to:
• receive a trip history for an operator of the vehicle, wherein the trip history includes trip information regarding a plurality of previous trips by the operator of the vehicle;
• generate a data cluster corresponding to each destination in the trip history by extracting a plurality of input features from trip information for each trip in the trip history, wherein the plurality of input features characterize a relationship between the operator of the vehicle and the plurality of previous trips and the plurality of input features for each data cluster includes at least one of the input features characterizes a current location for a newly initiated trip with respect to a destination for each of the plurality of previous trips;
• generate a training dataset based on collecting the data cluster corresponding to each of the destinations in the trip history;
• train a gradient boosted trees model utilizing the training dataset with hyperparameter tuning, wherein the hyperparameter tuning includes applying class weights to each of the plurality of input features based on their respective contribution to destination prediction in the gradient boosted trees model;
• and
• predict a plurality of possible destinations for the operator of the vehicle with the gradient boosted trees model utilizing an origin location of the operator of the vehicle, a time of day, and a day of the week as input conditions for the gradient boosted trees model;
• display a plurality of possible destinations on a display in the vehicle along with a confidence level that each of the plurality of possible destinations is a desired destination;
• and
• provide directions with a navigation system on the vehicle to the desired destination based on a selection by operator of the vehicle from the plurality of possible destinations on the display.