CPC G06Q 30/0278 (2013.01) [G06Q 10/06 (2013.01); G06Q 30/02 (2013.01); G06Q 30/0206 (2013.01)] | 20 Claims |
1. A computer-implemented method of used vehicle data processing, the method comprising:
receiving, from disparate data sources over a network by a backend process as inputs, vehicle trim data on vehicles over a past time period, vehicle manufacturer data on the vehicles when new, depreciation data on the vehicles or similar vehicle models, and vehicle price records on the vehicles, the backend process operated by a vehicle data system having a processor and a non-transitory computer-readable medium, the vehicle data system having a server computer that provides a web site or web service on Internet;
generating, by the backend process, estimates for parameters of a linear function used to determine current retail values of the vehicles;
applying, by the backend process, the determined current retail values of the vehicles to the vehicle price records;
constructing, by the backend process, a used vehicle research dataset including the current retail values of the vehicles as applied to the vehicle price records;
receiving, by the server computer through the web site or web service on the Internet, user input data including a zip code and vehicle year, make, model, trim, condition, and mileage of a used vehicle;
responsive to the user input data, constructing, by a frontend process based on the user input data, sets of regression variables including sets of regression variables constructed based on at least vehicle attributes of the used vehicle, the condition and mileage of the used vehicle, the zip code, the frontend process operated by the vehicle data system;
determining, by the frontend process using the zip code and the vehicle year, make, model, and trim of the used vehicle, a set of vehicles in a bin from the used vehicle research dataset, wherein each vehicle of the set of vehicles in the bin has the same vehicle year, make, model, and trim as the used vehicle and wherein each vehicle of the set of vehicles in the bin is in a geographic region inclusive of the zip code of the used vehicle;
determining, by the frontend process, an expected price of the used vehicle in the zip code using an average price for the used vehicle based on the current values of the set of vehicles in the bin from the used vehicle research dataset and a depreciated value of the used vehicle based on the sets of regression variables and the estimates for the parameters; and
presenting the expected price of the used vehicle in the zip code on a user device over the Internet.
|