IP Library › Granted Patent US 12,229,781
Granted Patent B2
US 12,229,781 · App. 17/510,203 · Granted Feb 18, 2025

Systems and methods for improved detection of network fraud events

Inventors: Joshua A. Allbright (Valley Park, MO); Christopher John Merz (Wildwood, MO)
Assignee: MASTERCARD INTERNATIONAL INCORPORATED
G06Q20/4016G06N20/00G06Q30/0185
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,229,781
App. No.
17/510,203
Granted
Feb 18, 2025
Kind
B2
Abstract

A method and system for detecting fraudulent network events in a payment card network are provided. A plurality of scored payment card transaction authorization requests is received, originating from a plurality of merchants, and data structures for each of a plurality of merchant groups are generated. Each data structure sorts the scored authorization requests into fraud score range stripes. The data structures are parsed over a plurality of time periods, and at least one cumulative metric is calculated for each merchant group for each of the time periods in each fraud score range stripe. A plurality of ratio striping values is determined for each merchant group, and a set of feature inputs is generated using the ratio striping values. A second fraud detection model is applied to the scored authorization requests. Parameters of the second fraud detection model are configured to change based on the generated set of feature inputs.

Claims (68)

1. A computing system for creating data structures used to detect fraudulent computer network events in a payment card network, the computing system comprising at least one processor and a memory storing instructions executable by the at least one processor to execute a merchant profiling engine configured to:

receive a plurality of scored payment card transaction authorization requests originating from a plurality of merchants, wherein each of the scored payment card transaction authorization requests is associated with a respective preliminary fraud score that is proportional to indicia of fraud present in an individual transaction corresponding to the respective scored payment card transaction authorization request;

generate, for each of a plurality of merchant groups of the plurality of merchants, a respective data structure within a computer memory, wherein the data structure is configured to sort the scored payment card transaction authorization requests associated with the respective merchant group over a plurality of fraud score range stripes, each of the fraud score range stripes defined by an upper fraud score threshold and a lower fraud score threshold and including one or more of the scored payment card transaction authorization requests having a value of the corresponding preliminary fraud score therebetween;

parse each of the data structures over a plurality of time periods, wherein each of the time periods extends back over a respective predetermined interval from a common starting point;

calculate, for each merchant group for each of the time periods, at least one cumulative metric from the one or more scored payment card transaction authorization requests associated with each of the fraud score range stripes;

determine, for each merchant group, a plurality of ratio striping values, each of the ratio striping values being a ratio of a first value of the at least one cumulative metric in a first of the fraud score range stripes from a first time period with respect to a second value of the at least one cumulative metric in the first fraud score range stripe from a second time period, wherein the second time period extends back farther in time than the first time period resulting in each of the plurality of ratio striping values being constrained to have values between zero and one;

generate a set of feature inputs using the determined plurality of ratio striping values, wherein each of the set of feature inputs is derived from a corresponding one of the plurality of ratio striping values, wherein the set of features is configured to periodically change as additional ratio striping values are determined, and wherein using the determined plurality of ratio striping values to generate the set of feature inputs increases a processing speed of the computing system;

train, using the set of feature inputs, one or more machine learning algorithms;

modify, using the trained one or more machine learning algorithms, parameters used to identify at least one potential fraud attack associated with the one or more scored payment card transaction authorization requests associated with the one of the merchant groups;

identify, by applying the modified parameters to the one or more scored payment card transaction authorization requests, the at least one potential attack;

generate, in response to a ratio striping value for a first fraud score range stripe for one of the merchant groups approaching a value of 1 and identifying the at least one potential fraud attack, a potential fraud attack alert, wherein the upper fraud score threshold of the first fraud score range stripe corresponds to a low indicia of the at least one potential fraud attack present in the individual scored payment card transaction authorization requests for the one of the merchant groups in the first fraud score range stripe; and

output the potential fraud attack alert to the one of the merchant groups.

2. The computing system of claim 1 , wherein the merchant profiling engine is further configured to:

receive additional scored payment card transaction authorization requests in near real-time with respect to the origination of the additional scored payment card transaction authorization requests by the plurality of merchants; and

add each of the additional scored payment card transaction authorization requests to the respective data structure for the respective merchant group of the plurality of merchant groups.

3. The computing system of claim 2 , wherein the merchant profiling engine is further configured to:

update the common starting point to a more recent time such that the additional scored payment card transaction authorization requests are included in the plurality of time periods;

re-parse, subsequent to the update, each of the data structures over the plurality of time periods; and

re-determine, for each merchant group, the plurality of ratio striping values based on the re-parsing.

4. The computing system of claim 3 , wherein the merchant profiling engine is further configured to purge older ones of the scored payment card transaction authorization requests from the respective data structure as the older ones age out of a longest time period of the plurality of time periods.

5. The computing system of claim 1 , wherein the merchant profiling engine is further configured to calculate the at least one cumulative metric including a tally of each scored payment card transaction authorization request scored within each fraud score range stripe over each of the plurality of time periods.

6. The computing system of claim 1 , wherein the merchant profiling engine is further configured to calculate the at least one cumulative metric including a cumulative total of transaction amounts of scored payment card transaction authorization requests scored within each fraud score range stripe over each of the plurality of time periods.

7. The computing system of claim 1 , wherein the merchant profiling engine is further configured to calculate the at least one cumulative metric including a count of declined scored payment card transaction authorization requests scored within each fraud score range stripe over each of the plurality of time periods.

8. A computer-implemented method for creating data structures used to detect fraudulent computer events in a payment card network, the method implemented by a computing device having at least one processor, the method comprising steps performed by the at least one processor of:

receiving a plurality of scored payment card transaction authorization requests originating from a plurality of merchants, wherein each of the scored payment card transaction authorization requests is associated with a respective preliminary fraud score that is proportional to indicia of fraud present in an individual transaction corresponding to the respective scored payment card transaction authorization request;

generating, for each of a plurality of merchant groups of the plurality of merchants, a respective data structure within a computer memory, wherein the data structure configured to sort the scored payment card transaction authorization requests associated with the respective merchant group over a plurality of fraud score range stripes, each of the fraud score range stripes defined by an upper fraud score threshold and a lower fraud score threshold and including one or more of the scored payment card transaction authorization requests having a value of the corresponding preliminary fraud score therebetween;

parsing each of the data structures over a plurality of time periods, wherein each of the time periods extends back over a respective predetermined interval from a common starting point;

calculating, for each merchant group for each of the time periods, at least one cumulative metric from the one or more scored payment card transaction authorization requests associated with each of the fraud score range stripes;

determining, for each merchant group, a plurality of ratio striping values, each of the ratio striping values being a ratio of a first value of the at least one cumulative metric in a first of the fraud score range stripes from a first time period with respect to a second value of the at least one cumulative metric in the first fraud score range stripe from a second time period, wherein the second time period extends back farther in time than the first time period resulting in each of the plurality of ratio striping values being constrained to have values between zero and one;

generating a set of feature inputs using the determined plurality of ratio striping values, wherein each of the set of feature inputs is derived from a corresponding one of the plurality of ratio striping values, wherein the set of features is configured to periodically change as additional ratio striping values are determined, and wherein using the determined plurality of ratio striping values to generate the set of feature inputs increases a processing speed of the computing system;

training, using the set of feature inputs, one or more machine learning algorithms;

modifying, using the trained one or more machine learning algorithms, parameters used to identify at least one potential fraud attack associated with the one or more scored payment card transaction authorization requests associated with the one of the merchant groups;

identifying, by applying the modified parameters to the one or more scored payment card transaction authorization requests, the at least one potential attack;

generating, in response to a ratio striping value for a first fraud score range stripe for one of the merchant groups approaching a value of 1 and identifying the at least one potential fraud attack, a potential fraud attack alert, wherein the upper fraud score threshold of the first fraud score range stripe corresponds to a low indicia of the at least one potential fraud attack present in the individual scored payment card transaction authorization requests for the one of the merchant groups in the first fraud score range stripe; and

outputting the potential fraud attack alert to the one of the merchant groups.

9. The method of claim 8 , further comprising:

receiving additional scored payment card transaction authorization requests in near real-time with respect to the origination of the additional scored payment card transaction authorization requests by the plurality of merchants; and

adding each of the additional scored payment card transaction authorization requests to the respective data structure for the respective merchant group of the plurality of merchant groups.

10. The method of claim 9 , further comprising:

updating the common starting point to a more recent time such that the additional scored payment card transaction authorization requests are included in the plurality of time periods;

re-parsing, subsequent to the update, each of the data structures over the plurality of time periods; and

re-determining, for each merchant group, the plurality of ratio striping values based on the re-parsing.

11. The method of claim 10 , further comprising purging older ones of the scored payment card transaction authorization requests from the respective data structure as the older ones age out of a longest time period of the plurality of time periods.

12. The method of claim 8 , further comprising calculating the at least one cumulative metric including a tally of each scored payment card transaction authorization request scored within each fraud score range stripe over each of the plurality of time periods.

13. The method of claim 8 , further comprising calculating the at least one cumulative metric including a cumulative total of transaction amounts of scored payment card transaction authorization requests scored within each fraud score range stripe over each of the plurality of time periods.

14. The method of claim 8 , further comprising calculating the at least one cumulative metric including a count of declined scored payment card transaction authorization requests scored within each fraud score range stripe over each of the plurality of time periods.

15. At least one non-transitory computer-readable storage medium having computer-executable instructions embodied thereon wherein, when executed by at least one processor of a computing system, the computer-executable instructions cause the at least one processor to:

receive a plurality of scored payment card transaction authorization requests originating from a plurality of merchants, wherein each of the scored payment card transaction authorization requests is associated with a respective preliminary fraud score that is proportional to indicia of fraud present in an individual transaction corresponding to the respective scored payment card transaction authorization request;

generate, for each of a plurality of merchant groups of the plurality of merchants, a respective data structure within a computer memory, wherein the data structure is configured to sort the scored payment card transaction authorization requests associated with the respective merchant group over a plurality of fraud score range stripes, each of the fraud score range stripes defined by an upper fraud score threshold and a lower fraud score threshold and including one or more of the scored payment card transaction authorization requests having a value of the corresponding preliminary fraud score therebetween;

parse each of the data structures over a plurality of time periods, wherein each of the time periods extends back over a respective predetermined interval from a common starting point;

calculate, for each merchant group for each of the time periods, at least one cumulative metric from the one or more scored payment card transaction authorization requests associated with each of the fraud score range stripes;

determine, for each merchant group, a plurality of ratio striping values, each of the ratio striping values being a ratio of a first value of the at least one cumulative metric in a first of the fraud score range stripes from a first time period with respect to a second value of the at least one cumulative metric in the first fraud score range stripe from a second time period, wherein the second time period extends back farther in time than the first time period resulting in each of the plurality of ratio striping values being constrained to have values between zero and one;

generate a set of feature inputs using the determined plurality of ratio striping values, wherein each of the set of feature inputs is derived from a corresponding one of the plurality of ratio striping values, wherein the set of features is configured to periodically change as additional ratio striping values are determined, and wherein using the determined plurality of ratio striping values to generate the set of feature inputs increases a processing speed of the computing system;

train, using the set of feature inputs, one or more machine learning algorithms;

modify, using the trained one or more machine learning algorithms, parameters used to identify at least one potential fraud attack associated with the one or more scored payment card transaction authorization requests associated with the one of the merchant groups;

identify, by applying the modified parameters to the one or more scored payment card transaction authorization requests, the at least one potential attack;

generate, in response to a ratio striping value for a first fraud score range stripe for one of the merchant groups approaching a value of 1 and identifying the at least one potential fraud attack, a potential fraud attack alert, wherein the upper fraud score threshold of the first fraud score range stripe corresponds to a low indicia of the at least one potential fraud attack present in the individual scored payment card transaction authorization requests for the one of the merchant groups in the first fraud score range stripe; and

output the potential fraud attack alert to the one of the merchant groups.

16. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to:

receive additional scored payment card transaction authorization requests in near real-time with respect to the origination of the additional scored payment card transaction authorization requests by the plurality of merchants; and

add each of the additional scored payment card transaction authorization requests to the respective data structure for the respective merchant group of the plurality of merchant groups.

17. The at least one non-transitory computer-readable storage medium of claim 16 , wherein the computer-executable instructions further cause the at least one processor to:

update the common starting point to a more recent time such that the additional scored payment card transaction authorization requests are included in the plurality of time periods;

re-parse, subsequent to the update, each of the data structures over the plurality of time periods; and

re-determine, for each merchant group, the plurality of ratio striping values based on the re-parsing.

18. The at least one non-transitory computer-readable storage medium of claim 17 , wherein the computer-executable instructions further cause the at least one processor to purge older ones of the scored payment card transaction authorization requests from the respective data structure as the older ones age out of a longest time period of the plurality of time periods.

19. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to calculate the at least one cumulative metric including a tally of each scored payment card transaction authorization request scored within each fraud score range stripe over each of the plurality of time periods.

20. The at least one non-transitory computer-readable storage medium of claim 15 , wherein the computer-executable instructions further cause the at least one processor to calculate the at least one cumulative metric including a cumulative total of transaction amounts of scored payment card transaction authorization requests scored within each fraud score range stripe over each of the plurality of time periods.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 25, 2021
From: ALLBRIGHT, JOSHUA A; MERZ, CHRISTOPHER JOHN
To: MASTERCARD INTERNATIONAL INCORPORATED
Reel/Frame 057905/0277 →
Continuity (2)
Continuation 16235074 · Dec 28, 2018
Related Publication 20220044250A1 · Feb 10, 2022
References Cited (154)
US 4371071A · Abedor · 1983 [cited by examiner]
US 6254000B1 · Degen et al. · 2001 [cited by applicant]
US 6658393B1 · Basch et al. · 2003 [cited by applicant]
US 7580891B2 · Klebanoff · 2009 [cited by applicant]
US 7788195B1 · Subramanian · 2010 [cited by applicant]
US 7814008B2 · Choudhuri et al. · 2010 [cited by applicant]
US 8266059B2 · Horvath et al. · 2012 [cited by applicant]
US 8423467B1 · Johansson et al. · 2013 [cited by applicant]
US 8489476B1 · Lester · 2013 [cited by applicant]
US 8600872B1 · Yan · 2013 [cited by applicant]
US 8606700B2 · Carlson et al. · 2013 [cited by applicant]
US 8612340B1 · Yan · 2013 [cited by applicant]
US 8620801B2 · Choudhuri et al. · 2013 [cited by applicant]
US 8694429B1 · Ballaro et al. · 2014 [cited by applicant]
US 8706641B2 · Bruesewitz et al. · 2014 [cited by applicant]
US 8744941B2 · Chisholm · 2014 [cited by applicant]
US 8744958B2 · Carlson et al. · 2014 [cited by applicant]
US 9230280B1 · Maag et al. · 2016 [cited by applicant]
US 9256780B1 · Howe · 2016 [cited by applicant]
US 9256810B2 · Wu et al. · 2016 [cited by applicant]
US 9256870B1 · Howe · 2016 [cited by applicant]
US 9331994B2 · Grigg et al. · 2016 [cited by applicant]
US 9392008B1 · Michel et al. · 2016 [cited by applicant]
US 9412108B2 · Wang et al. · 2016 [cited by applicant]
US 9477960B2 · Grigg et al. · 2016 [cited by applicant]
US 9483766B2 · Grigg et al. · 2016 [cited by applicant]
US 9547864B2 · Howe et al. · 2017 [cited by applicant]
US 9601000B1 · Gruss · 2017 [cited by examiner]
US 9619801B2 · Sikljovan · 2017 [cited by applicant]
US 9661012B2 · Michel et al. · 2017 [cited by applicant]
US 9721080B2 · Moran et al. · 2017 [cited by applicant]
US 9898741B2 · Siegel et al. · 2018 [cited by applicant]
US 10339606B2 · Gupta et al. · 2019 [cited by applicant]
US 10308033B2 · Moran et al. · 2019 [cited by applicant]
US 10380333B1 · Moran et al. · 2019 [cited by applicant]
US 10395243B1 · Johannson et al. · 2019 [cited by applicant]
US 10586235B2 · Wang et al. · 2020 [cited by applicant]
US 10778681B1 · Douglas et al. · 2020 [cited by applicant]
US 10867303B1 · Manapat et al. · 2020 [cited by applicant]
US 10937030B2 · Allbright et al. · 2021 [cited by applicant]
US 11151569B2 · Allbright · 2021 [cited by examiner]
US 11157913B2 · Allbright · 2021 [cited by examiner]
US 11366884B2 · Liu · 2022 [cited by applicant]
US 11521211B2 · Allbright · 2022 [cited by applicant]
US 20020099649A1 · Lee · 2002 [cited by applicant]
US 20030217094A1 · Andrews et al. · 2003 [cited by applicant]
US 20040034604A1 · Klebanoff · 2004 [cited by applicant]
US 20040162773A1 · Del Rey · 2004 [cited by applicant]
US 20050055373A1 · Forman · 2005 [cited by applicant]
US 20070094067A1 · Kumar et al. · 2007 [cited by applicant]
US 20070185782A1 · Shooks · 2007 [cited by applicant]
US 20070203732A1 · Griegel · 2007 [cited by examiner]
US 20090132347A1 · Anderson et al. · 2009 [cited by applicant]
US 20090132404A1 · King et al. · 2009 [cited by applicant]
US 20090276269A1 · Yee et al. · 2009 [cited by applicant]
US 20090307049A1 · Elliott, Jr. et al. · 2009 [cited by applicant]
US 20100228580A1 · Zoldi et al. · 2010 [cited by applicant]
US 20100280882A1 · Faith et al. · 2010 [cited by applicant]
US 20110055074A1 · Chen · 2011 [cited by examiner]
US 20110078034A1 · Hayhow · 2011 [cited by applicant]
US 20110238510A1 · Rowen et al. · 2011 [cited by applicant]
US 20120084207A1 · Horvath et al. · 2012 [cited by applicant]
US 20120239557A1 · Weinflash et al. · 2012 [cited by applicant]
US 20120296824A1 · Rosano · 2012 [cited by applicant]
US 20130036036A1 · Zoldi et al. · 2013 [cited by applicant]
US 20130159077A1 · Stringfellow et al. · 2013 [cited by applicant]
US 20130231976A1 · Tavares et al. · 2013 [cited by applicant]
US 20130297473A1 · Wolfe · 2013 [cited by applicant]
US 20140032409A1 · Rosano · 2014 [cited by applicant]
US 20140249934A1 · Subramanian et al. · 2014 [cited by applicant]
US 20140258099A1 · Rosano · 2014 [cited by applicant]
US 20140279185A1 · Merz et al. · 2014 [cited by applicant]
US 20140279331A1 · Gimby et al. · 2014 [cited by applicant]
US 20140324522A1 · Wilkins et al. · 2014 [cited by applicant]
US 20140337215A1 · Howe · 2014 [cited by applicant]
US 20150012430A1 · Chisholm et al. · 2015 [cited by applicant]
US 20150046338A1 · Laxminarayanan et al. · 2015 [cited by applicant]
US 20150073981A1 · Adjaoute · 2015 [cited by examiner]
US 20150127547A1 · Powell et al. · 2015 [cited by applicant]
US 20150220999A1 · Thornton et al. · 2015 [cited by applicant]
US 20150339667A1 · Dua · 2015 [cited by applicant]
US 20150339673A1 · Adjaoute · 2015 [cited by applicant]
US 20150348023A1 · Fisher et al. · 2015 [cited by applicant]
US 20150371207A1 · Cummins et al. · 2015 [cited by applicant]
US 20160125317A1 · Benjamin · 2016 [cited by applicant]
US 20160125405A1 · Alterman · 2016 [cited by applicant]
US 20160140561A1 · Cowan · 2016 [cited by applicant]
US 20160155124A1 · Howe et al. · 2016 [cited by applicant]
US 20160162759A1 · Yun et al. · 2016 [cited by applicant]
US 20160171498A1 · Wang et al. · 2016 [cited by applicant]
US 20160180333A1 · Leyva · 2016 [cited by applicant]
US 20160196615A1 · Yen et al. · 2016 [cited by applicant]
US 20160217470A1 · Gerard et al. · 2016 [cited by applicant]
US 20160321634A1 · George · 2016 [cited by applicant]
US 20160335641A1 · White et al. · 2016 [cited by applicant]
US 20160352766A1 · Flacher et al. · 2016 [cited by applicant]
US 20160364727A1 · DeLawter et al. · 2016 [cited by applicant]
US 20160364728A1 · DeLawter et al. · 2016 [cited by applicant]
US 20170053294A1 · Yang et al. · 2017 [cited by applicant]
US 20170116585A1 · Rosano · 2017 [cited by applicant]
US 20170140262A1 · Wilson et al. · 2017 [cited by applicant]
US 20170169500A1 · Merz et al. · 2017 [cited by applicant]
US 20170193515A1 · Sharan et al. · 2017 [cited by applicant]
US 20170293906A1 · Komarov · 2017 [cited by applicant]
US 20170352026A1 · Musil et al. · 2017 [cited by applicant]
US 20180018670A1 · Ju · 2018 [cited by examiner]
US 20180047024A1 · Niehaus · 2018 [cited by applicant]
US 20180053188A1 · Zoldi et al. · 2018 [cited by applicant]
US 20180114203A1 · Senci et al. · 2018 [cited by applicant]
US 20180182029A1 · Vinay · 2018 [cited by applicant]
US 20180218369A1 · Xiao et al. · 2018 [cited by applicant]
US 20190066109A1 · Jia · 2019 [cited by examiner]
US 20190073647A1 · Zoldi et al. · 2019 [cited by applicant]
US 20190130403A1 · Merz et al. · 2019 [cited by applicant]
US 20190220864A1 · Avegliano et al. · 2019 [cited by applicant]
US 20190220865A1 · Weber · 2019 [cited by applicant]
US 20190279309A1 · Gupta et al. · 2019 [cited by applicant]
US 20190385170A1 · Arrabothu · 2019 [cited by applicant]
US 20200211019A1 · Allbright · 2020 [cited by examiner]
US 20200211020A1 · Allbright · 2020 [cited by examiner]
US 20200211022A1 · Allbright et al. · 2020 [cited by applicant]
US 20200311285A1 · Jochems · 2020 [cited by applicant]
US 20210084065A1 · Irimie · 2021 [cited by examiner]
US 20210304207A1 · Lo Faro · 2021 [cited by applicant]
US 20210357940A1 · Benkreira · 2021 [cited by applicant]
US 20220012742A1 · Kielak et al. · 2022 [cited by applicant]
US 20220108331A1 · Thomson et al. · 2022 [cited by applicant]
US 20230316285A1 · Kramme · 2023 [cited by examiner]
CN 1348566A · 2002 [cited by applicant]
CN 105913243A · 2016 [cited by applicant]
EP 2420966A1 · 2012 [cited by applicant]
WO 2011077959A1 · 2001 [cited by applicant]
WO 2001077959A1 · 2001 [cited by applicant]
WO 2002025495A1 · 2002 [cited by applicant]
WO 2004070293A1 · 2004 [cited by applicant]
WO 2009067346A2 · 2009 [cited by applicant]
WO 2011025689A1 · 2011 [cited by applicant]
WO 2012135115A2 · 2012 [cited by applicant]
WO 2017031039A1 · 2017 [cited by applicant]
T. K. Behera and S. Panigrahi, “Credit Card Fraud Detection: A Hybrid Approach Using Fuzzy Clustering & Neural Network,” 2015 Second International Conference on Advances in Computing and Communication Engineering, Dehra… [cited by examiner]
J. T. S. Quah and M. Sriganesh, “Real Time Credit Card Fraud Detection using Computational Intelligence,” 2007 International Joint Conference on Neural Networks, Orlando, FL, USA, 2007, pp. 863-868, doi: 10.1109/IJCNN.2… [cited by examiner]
Ghosh and Reilly, “Credit card fraud detection with a neural-network,” 1994 Proceedings of the Twenty-Seventh Hawaii International Conference on System Sciences, Wailea, HI, USA, 1994, pp. 621-630, doi: 10.1109/HICSS.19… [cited by examiner]
Wikipedia, “Collaborative Filtering,” https://web.archive.org (Year: 2017). [cited by applicant]
Baboo et al. “Analysis of Spending Pattern on Credit Card Fraud Detection,” IOSR Journal of Computer Engineering, Mar.-Apr. 2017 (Year: 2017). [cited by applicant]
“Technology Briefs”, Publication Info: Card News; Potomac vol. 14, Iss. 4, Mar. 1999. [cited by applicant]
PCT International Search Report and Written Opinion, Application No. PCT/US2018/052145, dated Feb. 12, 2019, 12 pps. [cited by applicant]
U.S. Appl. No. 16/235,074, filed Dec. 28, 2018. [cited by applicant]
Baboo et al., “Analysis of Spending Pattern on Credit Card Detection,” IOSR Journal of Computer Engineering, Mar.-Apr. 2017 (Year: 2017). [cited by applicant]
PCT International Search Report and Written Opinion, Application No. PCT/US2018/052143, dated Dec. 7, 2018, 12 pages. [cited by applicant]
PCT International Search Report and Written Opinion, Application No. PCT/US2018/059326, dated Mar. 7, 2019, 11 pages. [cited by applicant]
PCT International Search Report and Written Opinion, Application No. PCT/US2018/031980, dated Jul. 26, 2018, 11 pages. [cited by applicant]
Roy et al., “Deep Learning Detecting Fraud in Credit Card Transactions”, 2018 Systems and Information Engineering Design Symposium (SIEDS), Charlottesville, VA, USA, 2018, pp. 129-134, doi: 10.1109/SIEDS.2018.8374722. [cited by applicant]
Sanchez-Aguayo et al., “Fraud Detection Using the Fraud Triangle Theory and Data Mining Techniques: A literature review”, Computers 10, 10:121, MDPI AG., (Year: 2021). [cited by applicant]
Sudjianto et al., “Statistical Methods for Fighting Financial Crimes”, Technometrics 52:1:5-19, American Society for Quality, Feb. 2010. [cited by applicant]
Cited By (1)
US 12,718,288