Context aware predictive activity evaluation

• US 10,373,248 B1
• Filed: 12/16/2016
• Issued: 08/06/2019
• Est. Priority Date: 12/16/2016
• Status: Active Grant

• Current Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Original Assignee: Wells Fargo Bank NA (Wells Fargo & Company)
• Inventors: Casey, Mary P., Loven, Kelly Francis, Blunt, Christopher J., Haseman, Lee Ryan, Mulvey, Richard
• Primary Examiner(s): Mitchell, Nathan A
• Application Number:
  US15/382,142
• Time in Patent Office: 963 Days
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 20/20 Point-of-sale [POS] network systems
• CPC Class Codes: G06Q 20/3223 Realising banking transactions through M-devices
• CPC Class Codes: G06Q 20/4012 Verifying personal identification numbers [PIN]
• CPC Class Codes: G06Q 20/405 Establishing or using transaction specific rules
• CPC Class Codes: G06Q 30/0625 Directed, with specific intent or strategy
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03
• CPC Class Codes: G06Q 40/128 Check-book balancing, updating or printing arrangements
• CPC Class Codes: H04W 4/021 Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences

Abstract

Systems and techniques for context aware predictive activity evaluation are described herein. A set of transaction variables may be identified for a predicted transaction. A set of inputs may be obtained corresponding to each transaction variable of the set of transaction variables. A value may be determined for each transaction variable using the set of inputs corresponding to each transaction variable of the set of transaction variables. The value for each transaction variable may be compared to a set of transaction models to select a transaction model for the predicted transaction. A probability may be calculated that the predicted transaction will be approved using the transaction model for the predicted transaction. The probability that the predicted transaction will be approved may be displayed on a display device.

Claims

1. A system for providing computer transaction pre-approval guidance, the system comprising:

at least one processor; and

a memory including instructions that, when executed by the at least one processor, cause the at least one processor to perform operations to;

obtain an image from a camera of a mobile device;

identify a set of product details using the image;

determine a predicted transaction using the set of product details;

identify a set of transaction variables for the predicted transaction;

obtain a set of inputs corresponding to each transaction variable of the set of transaction variables;

determine a value for each transaction variable using the set of inputs corresponding to each transaction variable of the set of transaction variables;

compare the value for each transaction variable to a set of transaction models to select a transaction model for the predicted transaction;

calculate, using the transaction model for the predicted transaction, a probability that the predicted transaction will be approved; and

display the probability that the predicted transaction will be approved on a display device.

2. The system of claim 1, further comprising operations to:

obtain a set of geolocation data from a mobile device;

identify a set of retailer information using the set of geolocation data; and

wherein determination of the predicted transaction includes using the set of retailer information.

3. The system of claim 2, further comprising operations to:

obtain a transaction history for a user; and

compare the transaction history to the set of retailer information, wherein determining the predicted transaction is based at least in part on the comparing.

4. The system of claim 1, wherein each transaction model of the set of transaction models comprises a set of transaction approval algorithms.

5. The system of claim 1, further comprising operations to:

identify an action that will increase the probability that the predicted transaction will be approved;

generate an interactive display element that, upon interaction, initiates the action; and

display the interactive display element simultaneous with the probability that the predicted transaction will be approved on the display device.

6. The system of claim 5, wherein the interactive display element initiates a balance transfer between a first account and a second account.

7. The system of claim 5, wherein the interactive display element initiates a product search against a list of products corresponding to an approved vendor.

8. The system of claim 1, wherein the set of inputs is obtained from a web browser tool bar and wherein displaying the probability that the predicted transaction will be approved on the display device uses the web browser tool bar.

9. The system of claim 1, wherein the set of inputs is obtained from a banking application and wherein displaying the probability that the predicted transaction will be approved on the display device uses the banking application.

10. The system of claim 1, further comprising operations to:

generate, based on the probability that the predicted transaction will be approved, a personal identification number corresponding to the predicted transaction; and

transmit the personal identification number corresponding to the predicted transaction to a banking application associated with an account of a user included in a transaction model of the set of transaction models.

11. The system of claim 10, wherein the personal identification number is capable of being entered at a point of sale terminal to complete a transaction.

12. At least one non-transitory computer readable medium including instructions for providing computer transaction pre-approval guidance that, when executed by a machine, cause the machine to perform operations to:

obtain an image from a camera of a mobile device;

identify a set of product details using the image;

determine a predicted transaction using the set of product details;

identify a set of transaction variables for the predicted transaction;

obtain a set of inputs corresponding to each transaction variable of the set of transaction variables;

determine a value for each transaction variable using the set of inputs corresponding to each transaction variable of the set of transaction variables;

compare the value for each transaction variable to a set of transaction models to select a transaction model for the predicted transaction;

calculate, using the transaction model for the predicted transaction, a probability that the predicted transaction will be approved; and

display the probability that the predicted transaction will be approved on a display device.

13. The at least one computer readable medium of claim 12, further comprising operations to:

obtain a set of geolocation data from a mobile device;

identify a set of retailer information using the set of geolocation data; and

wherein determination of the predicted transaction includes using the set of retailer information.

14. The at least one computer readable medium of claim 13, further comprising operations to:

obtain a transaction history for a user; and

compare the transaction history to the set of retailer information, wherein determining the predicted transaction is based at least in part on the comparing.

15. The at least one computer readable medium of claim 12, wherein each transaction model of the set of transaction models comprises a set of transaction approval algorithms.

16. The at least one computer readable medium of claim 12, further comprising operations to:

identify an action that will increase the probability that the predicted transaction will be approved;

generate an interactive display element that, upon interaction, initiates the action; and

display the interactive display element simultaneous with the probability that the predicted transaction will be approved on the display device.

17. The at least one computer readable medium of claim 16, wherein the interactive display element initiates a balance transfer between a first account and a second account.

18. The at least one computer readable medium of claim 16, wherein the interactive display element initiates a product search against a list of products corresponding to an approved vendor.

19. The at least one computer readable medium of claim 12, wherein the set of inputs is obtained from a web browser tool bar and wherein displaying the probability that the predicted transaction will be approved on the display device uses the web browser tool bar.

20. The at least one computer readable medium of claim 12, wherein the set of inputs is obtained from a banking application and wherein displaying the probability that the predicted transaction will be approved on the display device uses the banking application.

21. The at least one computer readable medium of claim 12, further comprising operations to:

generate, based on the probability that the predicted transaction will be approved, a personal identification number corresponding to the predicted transaction; and

transmit the personal identification number corresponding to the predicted transaction to a banking application associated with an account of a user included in a transaction model of the set of transaction models.

22. The at least one machine readable medium of claim 21, wherein the personal identification number is capable of being entered at a point of sale terminal to complete a transaction.

23. A method for providing computer transaction pre-approval guidance, the method comprising:

obtaining an image from a camera of a mobile device;

identifying a set of product details using the image;

determining a predicted transaction using the set of product details;

identifying a set of transaction variables for the predicted transaction;

obtaining a set of inputs corresponding to each transaction variable of the set of transaction variables;

determining a value for each transaction variable using the set of inputs corresponding to each transaction variable of the set of transaction variables;

comparing the value for each transaction variable to a set of transaction models to select a transaction model for the predicted transaction;

calculating, using the transaction model for the predicted transaction, a probability that the predicted transaction will be approved; and

displaying the probability that the predicted transaction will be approved on a display device.

24. The method of claim 23, further comprising:

obtaining a set of geolocation data from a mobile device;

identifying a set of retailer information using the set of geolocation data; and

wherein determining the predicted transaction includes using the set of retailer information.

25. The method of claim 24, further comprising:

obtaining a transaction history for a user; and

comparing the transaction history to the set of retailer information, wherein determining the predicted transaction is based at least in part on the comparing.

26. The method of claim 23, wherein each transaction model of the set of transaction models comprises a set of transaction approval algorithms.

27. The method of claim 23, further comprising:

identifying an action that will increase the probability that the predicted transaction will be approved;

generating an interactive display element that, upon interaction, initiates the action; and

displaying the interactive display element simultaneous with the probability that the predicted transaction will be approved on the display device.

28. The method of claim 27, wherein the interactive display element initiates a balance transfer between a first account and a second account.

29. The method of claim 27, wherein the interactive display element initiates a product search against a list of products corresponding to an approved vendor.

30. The method of claim 23, wherein the set of inputs is obtained from a web browser tool bar and wherein displaying the probability that the predicted transaction will be approved on the display device uses the web browser tool bar.

31. The method of claim 23, wherein the set of inputs is obtained from a banking application and wherein displaying the probability that the predicted transaction will be approved on the display device uses the banking application.

32. The method of claim 23, further comprising:

generating, based on the probability that the predicted transaction will be approved, a personal identification number corresponding to the predicted transaction; and

transmitting the personal identification number corresponding to the predicted transaction to a banking application associated with an account of a user included in a transaction model of the set of transaction models.

33. The method of claim 32, wherein the personal identification number is capable of being entered at a point of sale terminal to complete a transaction.