US 11,935,108 B1
Customer categorization and customized recommendations for automotive retail
Jayaprakash Vijayan, Dublin, CA (US); Gurusankar Sankararaman, Dublin, CA (US); Jagdish Mohanlal Patel, Fremont, CA (US); and Anant Sitaram, San Ramon, CA (US)
Assigned to Tekion Corp, Pleasanton, CA (US)
Filed by TEKION CORP, Pleasanton, CA (US)
Filed on Dec. 8, 2021, as Appl. No. 17/545,814.
Application 17/545,814 is a continuation of application No. 16/583,928, filed on Sep. 26, 2019, granted, now 11,227,322.
Claims priority of provisional application 62/737,100, filed on Sep. 26, 2018.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/00 (2023.01); G06N 20/00 (2019.01); G06Q 30/0601 (2023.01); G06Q 50/00 (2012.01)
CPC G06Q 30/0631 (2013.01) [G06N 20/00 (2019.01); G06Q 30/0611 (2013.01); G06Q 30/0621 (2013.01); G06Q 50/01 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A computer-implemented method of a management system for providing customized recommendations of products and services for customers of an automobile dealership, the computer-implemented method comprising:
accessing, by the management system, a plurality of sets of training customer profiles, each set of training customer profiles associated with a corresponding customer category from a plurality of customer categories of the automobile dealership and includes a plurality of training customer profiles that are assigned to the corresponding customer category, each customer category from the plurality of customer categories associated with a different level of importance to the automobile dealership;
extracting, for each set of training customer profiles from the plurality of sets of training customer profiles, features from the plurality of training customer profiles included in the set that are representative of the customer category corresponding to the set, the extracted features from each of the plurality of training customer profiles including a total amount of money spent at the automobile dealership, a frequency of purchases made at the automobile dealership, and a recency of a last purchase made at the automobile dealership;
training, by the management system, a categorization module of the management system to learn features associated with each of the plurality of customer categories using the extracted features from the plurality of training customer profiles included in the plurality of sets of training customer profiles, wherein the categorization module is a machine learned recency, frequency, and monetary analysis (RFMA) model;
storing a customer profile of a customer of the automobile dealership, the customer profile describing features of the customer including the customer's spending information at the automobile dealership, the spending information including a total amount of money spent by the customer at the automobile dealership, a frequency of purchases made by the customer at the automobile dealership, and a recency of a last purchase made by the customer at the automobile dealership;
applying, by the management system, the spending information of the customer to the trained categorization module of the management system to assign a customer category from the plurality of customer categories to the customer, the assigned customer category indicative of a level of importance of the customer to the automobile dealership;
generating, by the management system, a customized recommendation of at least one of a product or service for the customer to purchase from the automobile dealership according to the customer category assigned to the customer; and
providing, by the management system, the customized recommendation to the automobile dealership, the customized recommendation provided to the customer by the automobile dealership.