AI-based vehicle support system and method for use therewith
A vehicle transaction support system operates by: generating, based on customer prequalification data and extended bureau data and utilizing a customer grading engine having a first artificial intelligence model trained via machine learning, a customer grade that predicts a likelihood of transaction default associated with a customer; generating, based on customer profile data that includes the customer grade and other customer profile data and utilizing a vehicle recommendation engine having a second artificial intelligence model trained via machine learning, vehicle options data that indicates vehicles selected from a vehicle database; and generating, based on at least a portion of the customer profile data and the vehicle options data and utilizing a transaction recommendation engine having a third artificial intelligence model trained via machine learning, terms data associated with each of the vehicles selected from the vehicle database.
1. A vehicle transaction support system, comprising:
at least one processing system that includes a processor; and
at least one memory including a non-transitory computer readable storage medium that stores executable instructions that, when executed by the at least one processing system, cause performance of operations that include:
generating, based on customer prequalification data and extended bureau data and utilizing a customer grading engine having a first artificial intelligence model trained via machine learning, a customer grade that predicts a likelihood of transaction default associated with a customer, wherein the extended bureau data includes customer data received from a credit bureau that does not include a credit score;
generating, based on customer profile data that includes the customer grade and other customer profile data and utilizing a vehicle recommendation engine having a second artificial intelligence model trained via machine learning, vehicle options data that indicates vehicles selected from a vehicle database;
generating, based on at least a portion of the customer profile data and the vehicle options data and utilizing a transaction recommendation engine having a third artificial intelligence model trained via machine learning, terms data associated with each of the vehicles selected from the vehicle database;
sending the vehicle options data and terms data for display via a graphical user interface of a mobile device in a customer mode of operation of the mobile device; and
communicating agent data with the mobile device in an agent mode of the mobile device, wherein the agent data is not displayed via the graphical user interface of the mobile device in the customer mode of operation.
2. The vehicle transaction support system of claim 1 , wherein the operations further include:
receiving customer input data generated via customer interaction with a graphical user interface; and
generating the customer prequalification data and the other customer profile data from the customer input data.
3. The vehicle transaction support system of claim 1 , wherein the operations further include:
obtaining vehicle selection data and updated terms data generated via customer interaction with the graphical user interface; and
comparing the updated terms data to term limits data;
generating transaction feedback data indicating acceptance of the updated terms data for display via the graphical user interface, when the updated terms data compare favorably to the term limits data; and
generating transaction feedback data indicating rejection of the updated terms for display via the graphical user interface, when the updated terms data compare unfavorably to the term limits data.
4. The vehicle transaction support system of claim 1 , wherein the first artificial intelligence model is an ensemble model that includes:
a plurality of auto encoding sub-models configured to process the customer prequalification data and the extended bureau data; and
a master sub-model configured to generate the customer grade by processing the customer prequalification data and the extended bureau data together with outputs of the plurality of auto encoding sub-models.
5. The vehicle transaction support system of claim 1 , wherein the second artificial intelligence model is an ensemble model that includes:
a vehicle category selection sub-model configured to generate a selected vehicle category from a plurality of vehicle categories based on the customer profile data;
a vehicle parameter selection sub-model configured to generate a plurality of vehicle parameters for the selected vehicle category based on the customer profile data; and
a vehicle search engine configured to generate the vehicles selected from the vehicle database based on a search of the vehicle database for vehicles having vehicle data that compares favorably to the vehicle parameters.
6. The vehicle transaction support system of claim 1 , wherein the third artificial intelligence model is an ensemble model that includes:
a transaction parameter selection sub-model configured to generate, based on the at least a portion of the customer profile data, transaction parameters that indicate a collection of deal terms predicted for acceptance; and
a terms selection sub-model configured to generate, based on the transaction parameters and the vehicle options data, the terms data associated with each of the vehicles selected from the vehicle database.
7. The vehicle transaction support system of claim 6 , wherein the terms selection sub-model is an ensemble model that includes:
a first sub-model trained to generate, based on the at least a portion of the customer profile data, the transaction parameters, and the vehicle options data, a net present value based on non-defaulting transactions;
a second sub-model trained to generate, based on the at least a portion of the customer profile data, the transaction parameters, and the vehicle options data, a net present value based on defaulting transactions;
a third sub-model trained to generate, based on the at least a portion of the customer profile data, the transaction parameters, and the vehicle options data, probability of default;
a net present value function configured to generate the terms data associated with each of the vehicles selected from the vehicle database, based on outputs from the first sub-model, the second sub-model and the third sub-model.
8. A method comprising:
generating, based on customer prequalification data and extended bureau data and utilizing a customer grading engine having a first artificial intelligence model trained via machine learning, a customer grade that predicts a likelihood of transaction default associated with a customer, wherein the extended bureau data includes customer data received from a credit bureau that does not include a credit score;
generating, based on customer profile data that includes the customer grade and other customer profile data and utilizing a vehicle recommendation engine having a second artificial intelligence model trained via machine learning, vehicle options data that indicates vehicles selected from a vehicle database;
generating, based on at least a portion of the customer profile data and the vehicle options data and utilizing a transaction recommendation engine having a third artificial intelligence model trained via machine learning, terms data associated with each of the vehicles selected from the vehicle database;
sending the vehicle options data and terms data for display via a graphical user interface of a mobile device in a customer mode of operation of the mobile device; and
communicating agent data with the mobile device in an agent mode of the mobile device, wherein the agent data is not displayed via the graphical user interface of the mobile device in the customer mode of operation.
9. The method of claim 8 , further comprising:
receiving customer input data generated via customer interaction with the graphical user interface; and
generating the customer prequalification data and the other customer profile data from the customer input data.
10. The method of claim 8 , further comprising:
obtaining vehicle selection data and updated terms data generated via customer interaction with the graphical user interface;
comparing the updated terms data to term limits data;
generating transaction feedback data indicating acceptance of the updated terms data for display via the graphical user interface, when the updated terms data compare favorably to the term limits data; and
generating transaction feedback data indicating rejection of the updated terms for display via the graphical user interface, when the updated terms data compare unfavorably to the term limits data.
11. The method of claim 8 , wherein the first artificial intelligence model is an ensemble model that includes:
a plurality of auto encoding sub-models configured to process the customer prequalification data and the extended bureau data; and
a master sub-model configured to generate the customer grade by processing the customer prequalification data and the extended bureau data together with outputs of the plurality of auto encoding sub-models.
12. The method of claim 8 , wherein the second artificial intelligence model is an ensemble model that includes:
a vehicle category selection sub-model configured to generate a selected vehicle category from a plurality of vehicle categories based on the customer profile data;
a vehicle parameter selection sub-model configured to generate a plurality of vehicle parameters for the selected vehicle category based on the customer profile data; and
a vehicle search engine configured to generate the vehicles selected from the vehicle database based on a search of the vehicle database for vehicles having vehicle data that compares favorably to the vehicle parameters.
13. The method of claim 8 , wherein the third artificial intelligence model is an ensemble model that includes:
a transaction parameter selection sub-model configured to generate, based on the at least a portion of the customer profile data, transaction parameters that indicate a collection of deal terms predicted for acceptance; and
a terms selection sub-model configured to generate, based on the transaction parameters and the vehicle options data, the terms data associated with each of the vehicles selected from the vehicle database.
14. The method of claim 13 , wherein the terms selection sub-model is an ensemble model that includes:
a first sub-model trained to generate, based on the at least a portion of the customer profile data, the transaction parameters, and the vehicle options data, a net present value based on non-defaulting transactions;
a second sub-model trained to generate, based on the at least a portion of the customer profile data, the transaction parameters, and the vehicle options data, a net present value based on defaulting transactions;
a third sub-model trained to generate, based on the at least a portion of the customer profile data, the transaction parameters, and the vehicle options data, probability of default; and
a net present value function configured to generate the terms data associated with each of the vehicles selected from the vehicle database, based on outputs from the first sub-model, the second sub-model and the third sub-model.