US 12,131,345 B2
System and method for dealer evaluation and dealer network optimization using spatial and geographic analysis in a network of distributed computer systems
Michael D. Swinson, Santa Monica, CA (US); Christopher James O'Keeffe, Oak Park, CA (US); Daniel Salazar, Torrance, CA (US); and Ludovica Rizzo, Los Angeles, CA (US)
Assigned to TrueCar, Inc., Santa Monica, CA (US)
Filed by TrueCar, Inc., Santa Monica, CA (US)
Filed on Feb. 2, 2021, as Appl. No. 17/165,584.
Application 17/165,584 is a continuation of application No. 15/855,542, filed on Dec. 27, 2017, granted, now 10,963,897.
Claims priority of provisional application 62/440,222, filed on Dec. 29, 2016.
Prior Publication US 2021/0158382 A1, May 27, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/02 (2023.01); G06F 16/951 (2019.01); G06Q 30/0201 (2023.01); G06Q 30/0204 (2023.01)
CPC G06Q 30/0205 (2013.01) [G06F 16/951 (2019.01); G06Q 30/0201 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A vehicle data system for determining and utilizing spatial or geography based metrics in a distributed computing environment based on enhanced data obtained from distributed sources, comprising:
a plurality of computing devices coupled to one another, one or more user computer devices, and a plurality of distributed data sources over a network, wherein:
a first computer device of the vehicle data system performs a process including:
obtaining a set of historical transaction data associated with a vehicle make from a first distributed data source, where the set of historical transaction data comprises data on transactions associated with vehicles of the vehicle make;
applying one or more transformations to the set of historical transaction data to create a modified set of historical transaction data that includes additional vehicle data collected from a second distributed data sources by VIN by correlating the additional vehicle data collected from the second distributed data sources with data on transactions of the set of historical transaction data;
determining a competition zone index for a first dealer, a geographic area and a make of vehicle, the competition zone index quantifying the competitiveness of the first dealer in the geographic area, wherein determining a competition zone index comprises determining a distance between the geographic area and the first dealer, a distance between the geographic area and a closest second dealer, and a typical distance traveled from the zip code to purchase a vehicle of the vehicle make;
creating a first training set of historical transaction data, the first training set comprising historical transaction data and modified historical transaction data;
training a universal sales model at a first time using the first training set based on the competition zone;
creating a second training set of historical transaction data, the second training set comprising modified historical transaction datal;
training the universal sales model at a second time using the second training set based on the competition zone;
receiving a request, the request associated with the first dealer and specifying the make;
identifying a set of geographic areas within a distance of the first dealer;
determining a predicted number of sales for the first dealer in a geographic area of the set of geographic areas based on the competition zone index for the first dealer and the universal sales model;
generating an interface providing a visual representation of the geographic area and the predicted number of sales of the geographic area associated with the first dealer and the vehicle make; and
responding to the request by distributing the generated interface over the network.