US 11,734,690 B1
Heuristic money laundering detection engine
Elizabeth A. Flowers, Bloomington, IL (US); Puneit Dua, Bloomington, IL (US); Eric Balota, Bloomington, IL (US); and Shanna L. Phillips, Bloomington, IL (US)
Assigned to State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed by State Farm Mutual Automobile Insurance Company, Bloomington, IL (US)
Filed on Oct. 8, 2020, as Appl. No. 17/66,319.
Application 17/066,319 is a continuation of application No. 15/495,603, filed on Apr. 24, 2017, granted, now 10,832,249.
Claims priority of provisional application 62/368,448, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,359, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,298, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,588, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,536, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,332, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,271, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,525, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,572, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,503, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,406, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,548, filed on Jul. 29, 2016.
Claims priority of provisional application 62/368,512, filed on Jul. 29, 2016.
Claims priority of provisional application 62/337,711, filed on May 17, 2016.
Claims priority of provisional application 62/335,374, filed on May 12, 2016.
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 20/40 (2012.01); G06Q 40/00 (2023.01); G06Q 30/00 (2023.01); G06Q 40/12 (2023.01); G06Q 30/018 (2023.01)
CPC G06Q 20/4016 (2013.01) [G06Q 30/018 (2013.01); G06Q 40/12 (2013.12)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
retrieving, by one or more processors, a first transaction set comprising unstructured transaction data associated with a plurality of users, wherein the first transaction set includes at least one indication of money laundering activity;
generating, by the one or more processors, a heuristic algorithm by training a machine learning model, based on the first transaction set, to identify predictive characteristics of the unstructured transaction data that are predictive of the at least one indication of money laundering activity;
receiving, by the one or more processors, a request for a money laundering activity report corresponding to a transaction history associated with a particular financial account;
retrieving, by the one or more processors, and in response to the request, a second transaction set associated with a plurality of historical financial transactions corresponding to the particular financial account;
generating, by the one or more processors, using the heuristic algorithm, and based at least in part on instances of the predictive characteristics indicated in the second transaction set, a predicted indication of money laundering activity associated with the particular financial account;
generating, by the one or more processors, the money laundering activity report, wherein the money laundering activity report indicates the predicted indication of money laundering activity; and
updating, by the one or more processors, the heuristic algorithm by re-training the machine learning model based at least in part on the at least one indication of money laundering activity and the predicted indication of money laundering activity.