US 11,790,269 B1
Systems and methods for generating dynamic models based on trigger events
Erik Peter Hjermstad, Lincoln, NE (US); Tony T. Morris, Huntington Beach, CA (US); Heidi Beth Haupt, Streamwood, IL (US); and Jennifer Kuhr Schwartz, Lincoln, NE (US)
Assigned to Experian Information Solutions, Inc., Costa Mesa, CA (US)
Filed by Experian Information Solutions, Inc., Costa Mesa, CA (US)
Filed on Sep. 27, 2021, as Appl. No. 17/486,295.
Application 17/486,295 is a continuation of application No. 16/246,083, filed on Jan. 11, 2019, granted, now 11,157,835.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); G06N 5/025 (2023.01); G06F 16/335 (2019.01); G06F 16/23 (2019.01); G06F 16/21 (2019.01); G06F 9/54 (2006.01)
CPC G06N 20/00 (2019.01) [G06F 9/542 (2013.01); G06F 16/212 (2019.01); G06F 16/2365 (2019.01); G06F 16/337 (2019.01); G06N 5/025 (2013.01)] 23 Claims
OG exemplary drawing
 
1. A data processing system comprising:
a client database including a plurality of client records relating to a plurality of vehicles associated with a plurality of clients, wherein each client record includes contact information for a client and information relating to at least one vehicle associated with the client;
a hardware processor configured to execute computer-executable instructions to:
verify that each of the plurality of client records conforms to a set of formatting guidelines;
apply a first data filter to each of the plurality of client records to generate a vehicle data subfile comprising records for each vehicle associated with one of the clients having a record in the client database;
apply a second data filter to the plurality of client records to generate a client data subfile comprising information for each of the clients having a record in the client database;
monitor the vehicle data subfile and the client data subfile for one or more trigger event records, wherein the one or more trigger event records identifies one or more of: a vehicle event or a client event;
generate a first dynamic model for determining a likelihood that a client associated with the one or more trigger event records will perform a particular action, based on the one or more trigger events and associated with one or more of: a loyalty propensity predicting a likelihood of being loyal to a vehicle make with which a respective client is already associated, or buy propensity predicting a likelihood of acquiring a vehicle with which the respective client is not already associated;
apply the first dynamic model to generate at least one score value associated with the at least one trigger event record, wherein the at least one score value provides a value representative of the predicted likelihood that the client will perform the particular action;
generate a notification including one or more of: the generated at least one score value, the one or more trigger event records, or information associated with the one or more trigger event records; and
an electronic input/output communication interface configured to receive the plurality of client records from a user device and transmit the instructions for rendering a user interface providing the notification on the user device.