Fraud prevention systems and methods for a price comparison system

• US 10,467,645 B2
• Filed: 05/30/2014
• Issued: 11/05/2019
• Est. Priority Date: 01/30/2013
• Status: Active Grant

• Current Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Original Assignee: Walmart Apollo, LLC (WalMart Inc.)
• Inventors: Wang, Joseph Y., Rapaka, Venkata Syam Prakash, Parekh, Vivek, Hatch, Paul Kay, Benson, Ronald G., Bolla, Srirama M.
• Primary Examiner(s): Sittner, Matthew T
• Assistant Examiner(s): Ezewoko, Michael I
• Application Number:
  US14/292,681
• Publication Number:
  US 20140278883A1
• Time in Patent Office: 1,985 Days
• Field of Search: 705 1434
• CPC Class Codes: G06Q 30/0225 Avoiding frauds
• CPC Class Codes: G06Q 30/0234 Rebates after completed purchase

Abstract

Systems and methods are disclosed for evaluating a transaction concluded at a POS (point of sale) device. Prices for competitive retail stores within a geographic region of the POS may be evaluated after concluding a transaction. Price differences between items and corresponding prices in the third party data are identified. Where the purchase price exceeds the corresponding third-party price, a credit is assigned to the customer, such as in the form of a gift card or code that may be redeemed in a subsequent transaction. Credits may also be assigned to a debit card associated with a user, either with or without applying some multiplier. Transactions may be compared to past transaction of a user in order to detect fraud. Recent activity may be flagged as potentially fraudulent and reviewed before providing a credit.

Claims

1. A system comprising:

a sale terminal configured to generate user transaction data representing one or more historical transactions conducted by a user at the sale terminal;

one or more processors; and

one or more memory devices operably coupled to the one or more processors, the one or more memory devices storing executable and operational code effective to cause the one or more processors and the one or more memory devices to operate as a savings module, a fraud detection module, a validation module, and a redemption module,

wherein;

the one or more memory devices store the user transaction data for the user, a return history for the user, and a network history of the user representing a history of electronic interactions of the user with a server system;

the savings module is configured to, for a first transaction of the user, determine one or more price differences between prices paid for items of the first transaction and third party prices paid for the items;

the fraud detection module is coupled to the savings module and configured to perform;

receiving inputs including (a) the user transaction data, (b) the return history, and (c) the network history;

determining whether a difference between recent shopping activity and historical shopping activity of the user indicates fraud based on the inputs, wherein the historical shopping activity is associated with a first time period that precedes a second time period associated with the recent shopping activity, wherein the determining whether the difference between the recent shopping activity and the historical shopping activity of the user indicates fraud further comprises;

responsive to the inputs, determining that the historical shopping activity indicates a first frequency of purchase transactions during the first time period;

determining that the recent shopping activity indicates a second frequency of purchase transactions during the second time period;

evaluating whether a first difference between the second frequency of purchase transactions and the first frequency of purchase transactions exceeds a first threshold value, as defined by R₁−

H₁>

T₁, where R₁ is the second frequency of purchase transactions, H₁ is the first frequency of purchase transactions, and T₁ is the first threshold value;

responsive to the inputs, determining that the historical shopping activity indicates a first frequency of return transactions during the first time period;

determining that the recent shopping activity indicates a second frequency of return transactions during the second time period;

evaluating whether a second difference between the second frequency of return transactions and the first frequency of return transactions exceeds a second threshold value, as defined by R₂−

H₂>

T₂, where R₂ is the second frequency of return transactions, H₂ is the first frequency of return transactions, and T₂ is the second threshold value;

determining that the historical shopping activity indicates purchases among a first plurality of categories;

determining that the recent shopping activity indicates purchases among at least one second category;

evaluating whether the at least one second category belongs to one of the first plurality of categories;

determining that the historical shopping activity indicates online activity during the first time period from at least one of a first device, a first browser type, or a first internet protocol address;

determining that the recent shopping activity indicates online activity during the second time period from at least one of a second device, a second browser type, or a second internet protocol address;

evaluating a third difference between (i) the first device, the first browser type, or the first internet protocol address and (ii) the second device, the second browser type, or the second internet protocol address;

determining that the historical shopping activity indicates a first average credit per transaction during the first time period based on third party pricing data;

determining that the recent shopping activity indicates a second average credit per transaction during the second time period based on the third party pricing data; and

evaluating whether a fourth difference between the second average credit per transaction and the first average credit per transaction exceeds a third threshold value; and

when the difference between the recent shopping activity and the historical shopping activity indicates fraud, generating a flag with respect to the first transaction;

the validation module is coupled to the fraud detection module and is configured to (1) receive a validation decision from the fraud detection module, (2) when the validation decision indicates rejection, refrain from crediting an account associated with a user identifier identifying the user with an amount corresponding to the one or more price differences, and (3) when the difference between the recent shopping activity and the historical shopping activity does not indicate fraud and the validation decision indicates acceptance, perform at least one of;

(i) crediting the account associated with the user identifier with the amount corresponding to the one or more price differences, (ii) generating a redemption code having the amount corresponding to the one or more price differences and receive a request to redeem the redemption code from the user associated with the user identifier, or (iii) issuing a gift card to the user associated with the user identifier; and

the redemption module is coupled to the sale terminal, and is configured to receive transaction information related to a subsequent sale at the sale terminal and to transmit an authorization to the sale terminal when the transaction information is valid, the authorization allowing the sale terminal to apply the amount as credited, to the subsequent sale.

2. The system of claim 1, wherein the executable and operational code are further effective to identify for each item of the items of the first transaction, a third party price of the third party prices corresponding to the each item by:

identifying a geographic location of the sale terminal at which the first transaction was concluded.

3. The system of claim 2, wherein the executable and operational code are further effective to identify for each item of the items of the first transaction, the third party price of the third party prices corresponding to the each item by:

identifying as the third party price for the each item a price offered for the each item at a retail location within a threshold distance from the geographic location of the sale terminal at which the first transaction was concluded.

4. The system of claim 1, wherein the executable and operational code are further effective to receive a record of the first transaction concluded on the sale terminal by:

receiving, from a user computer, a transaction identifier.

5. The system of claim 4, wherein the executable and operational code are further effective to receive the record of the first transaction concluded on the sale terminal by:

retrieving the record of the first transaction using the transaction identifier.

6. The system of claim 1, wherein the executable and operational code are further effective to evaluate whether a difference between the second average credit per transaction and the first average credit per transaction exceeds a third threshold condition indicates fraud, is defined by R₃−

H₃>

T₃, where R₃ is a recent return frequency, H₃ is a historical return frequency, and T₃ is the third threshold value.

7. The system of claim 1, wherein the executable and operational code are further effective to:

identify for each item of the items of the first transaction, a third party price of the third party prices corresponding to the each item by;

identifying a geographic location of the sale terminal at which the first transaction was concluded; and

identifying as the third party price for the each item a price offered for the each item at a retail location within a threshold distance from the geographic location of the sale terminal at which the first transaction was concluded; and

receive a record of the first transaction concluded on the sale terminal by;

receiving, from a user computer, a transaction identifier.

8. The system of claim 7, wherein the executable and operational code are further effective to effective to receive a record of the first transaction concluded on the sale terminal by:

retrieving the record of the first transaction using the transaction identifier.

9. A computer program product, the computer program product being embodied in a non-transitory computer readable storage medium and comprising computer instructions for a computer system, the computer instructions causing the computer system to perform:

receiving a record of a first transaction concluded on a sale terminal, the record including a user identifier, one or more item identifiers, and a price paid for each item identifier of the one or more item identifiers;

storing the record of the first transaction in a user record as user transaction data, the user record also including a return history for a user, and a network history of the user representing a history of electronic interactions of the user with a server system;

subsequent to the first transaction, identifying for the each item identifier of at least a portion of the one or more item identifiers, a third party record, the third party record corresponding to the each item identifier and having a third party price for the each item identifier;

subsequent to the first transaction, identifying one or more discounted identifiers of the one or more item identifiers, the third party prices of the third party records corresponding to the one or more discounted identifiers being less than the price paid for the one or more discounted identifiers by one or more price differences;

evaluating recent shopping activity associated with the user identifier;

evaluating historical shopping activity associated with the user identifier based on a plurality of inputs including (1) the user transaction data, (2) the return history, and (3) the network history, the historical shopping activity including shopping activity preceding the recent shopping activity;

determining whether a difference between the recent shopping activity and the historical shopping activity indicates fraud based on the inputs, wherein the historical shopping activity is associated with a first time period that precedes a second time period associated with the recent shopping activity, wherein the determining whether the difference between the recent shopping activity and the historical shopping activity of the user indicates fraud further comprises;

responsive to the inputs, determining that the historical shopping activity indicates a first frequency of purchase transactions;

determining that the recent shopping activity indicates a second frequency of purchase transactions;

evaluating whether a first difference between the second frequency of purchase transactions and the first frequency of purchase transactions exceeds a first threshold value, as defined by R₁−

H₁>

T₁, where R₁ is the second frequency of purchase transactions, H₁ is the first frequency of purchase transactions, and T₁ is the first threshold value;

responsive to the inputs, determining that the historical shopping activity indicates a first frequency of return transactions during the first time period;

determining that the recent shopping activity indicates a second frequency of return transactions during the second time period;

evaluating whether a second difference between the second frequency of return transactions and the first frequency of return transactions exceeds a second threshold value, as defined by R₂−

H₂>

T₂, where R₂ is the second frequency of return transactions, H₂ is the first frequency of return transactions, and T₂ is the second threshold value;

determining that the historical shopping activity indicates purchases among a first plurality of categories;

determining that the recent shopping activity indicates purchases among at least one second category;

evaluating whether the at least one second category belongs to one of the first plurality of categories;

determining that the historical shopping activity indicates online activity during the first time period from at least one of a first device, a first browser type, or a first internet protocol address;

determining that the recent shopping activity indicates online activity during the second time period from at least one of a second device, a second browser type, or a second internet protocol address;

evaluating a third difference between (i) the first device, the first browser type, or the first internet protocol address and (ii) the second device, the second browser type, or the second internet protocol address;

determining that the historical shopping activity indicates a first average credit per transaction during the first time period based on third party pricing data;

determining that the recent shopping activity indicates a second average credit per transaction during the second time period based on the third party pricing data; and

evaluating whether a fourth difference between the second average credit per transaction and the first average credit per transaction exceeds a third threshold value;

when the difference between the recent shopping activity and the historical shopping activity indicates fraud, generating a flag with respect to the first transaction;

receiving a validation decision;

when the validation decision indicates approval, crediting an account associated with the user identifier with an amount corresponding to the one or more price differences;

when the validation decision indicates rejection, refraining from crediting an account associated with the user identifier with the amount corresponding to the one or more price differences;

when the difference between the recent shopping activity and the historical shopping activity does not indicate fraud and the validation decision indicates acceptance, perform at least one of;

(i) crediting the account associated with the user identifier with the amount corresponding to the one or more price differences, (ii) generating a redemption code having the amount corresponding to the one or more price differences and receive a request to redeem the redemption code from the user associated with the user identifier, or (iii) issuing a gift card to the user associated with the user identifier;

receiving, at the sale terminal, transaction information related to a second transaction subsequent to the first transaction;

transmitting an authorization to the sale terminal when the transaction information is valid, the authorization allowing the sale terminal to apply an amount to be credited to the second transaction subsequent to the first transaction; and

applying the amount of credit in the account associated with the user identifier toward a purchase price of the second transaction subsequent to the first transaction.

10. The computer program product of claim 9, wherein the identifying the each item identifier of the at least the portion of the one or more item identifiers, the third party record, the third party record corresponding to the each item identifier and having the third party price for the each item identifier further comprises:

identifying a geographic location of the sale terminal.

11. The computer program product of claim 10, wherein the identifying the each item identifier of the at least the portion of the one or more item identifiers, the third party record, the third party record corresponding to the each item identifier and having the third party price for the each item identifier further comprises:

identifying as the third party record for the each item identifier of the at least the portion of the one or more item identifiers the third party record corresponding to a retail location within a threshold distance from the geographic location of the sale terminal.

12. The computer program product of claim 11, wherein the identifying the each item identifier of the at least the portion of the one or more item identifiers, the third party record, the third party record corresponding to the each item identifier and having the third party price for the each item identifier further comprises:

excluding third party records corresponding to retail locations outside of the threshold distance from the geographic location.

13. The computer program product of claim 9, wherein the receiving the record of the first transaction concluded on the sale terminal further comprises:

receiving, from a user computer, a transaction identifier.

14. The computer program product of claim 13, wherein the receiving the record of the first transaction concluded on the sale terminal further comprises:

retrieving the record of the first transaction using the transaction identifier.

15. The computer program product of claim 9, wherein the evaluating whether a difference between the second average credit per transaction and the first average credit per transaction exceeds a third threshold condition indicates fraud, is defined by R₃−

H₃>

T₃, where R₃ is a recent return frequency, H₃ is a historical return frequency, and T₃ is the third threshold value.

16. The computer program product of claim 9, wherein:

the identifying the each item identifier of the at least the portion of the one or more item identifiers, the third party record, the third party record corresponding to the each item identifier and having the third party price for the each item identifier further comprises;

identifying a geographic location of the sale terminal; and

identifying as the third party record for the each item identifier of the at least the portion of the one or more item identifiers the third party record corresponding to a retail location within a threshold distance from the geographic location of the sale terminal and excluding third party records corresponding to retail locations outside of the threshold distance from the geographic location; and

the receiving the record of the first transaction concluded on the sale terminal further comprises;

receiving, from a user computer, a transaction identifier.

17. The computer program product of claim 16, wherein the receiving the record of the first transaction concluded on the sale terminal further comprises:

retrieving the record of the first transaction using the transaction identifier.

18. A method of operating a computer system, the computer system including one or more processors and one or more memory devices operably coupled to the one or more processors, the one or more memory devices storing executable and operational code effective to cause the one or more processors and the one or more memory devices to operate as a savings module, a fraud detection module, a validation module and a redemption module, the method comprising:

receiving, at the savings module, a record of a first transaction concluded on a sale terminal, the record including a user identifier, one or more item identifiers and a price paid for each item identifier of the one or more item identifiers;

storing the record of the first transaction in a user record as user transaction data, the user record also including a return history for a user, and a network history of the user representing a history of electronic interactions of the user with a server system;

subsequent to the first transaction, identifying, by the savings module, for the each item identifier of at least a portion of the one or more item identifiers, a third party record, the third party record corresponding to the each item identifier and having a third party price for the each item identifier;

subsequent to the first transaction, identifying, by the savings module, one or more discounted identifiers of the one or more item identifiers, the third party prices of the third party records corresponding to the one or more discounted identifiers being less than the price paid for the one or more discounted identifiers by one or more price differences;

evaluating, by the fraud detection module, recent shopping activity associated with the user identifier;

evaluating, by the fraud detection module, historical shopping activity associated with the user identifier based on a plurality of inputs including (1) the user transaction data, (2) the return history, and (3) the network history, the historical shopping activity including shopping activity preceding the recent shopping activity;

determining, by the fraud detection module, whether a difference between the recent shopping activity and the historical shopping activity indicates fraud based on the inputs, wherein the historical shopping activity is associated with a first time period that precedes a second time period associated with the recent shopping activity, wherein the determining whether the difference between the recent shopping activity and the historical shopping activity of the user indicates fraud further comprises;

responsive to the inputs, determining that the historical shopping activity indicates a first frequency of purchase transactions;

determining that the recent shopping activity indicates a second frequency of purchase transactions;

evaluating whether a first difference between the second frequency of purchase transactions and the first frequency of purchase transactions exceeds a first threshold value, as defined by R₁−

H₁>

T₁, where R₁ is the second frequency of purchase transactions, H₁ is the first frequency of purchase transactions, and T₁ is the first threshold value;

responsive to the inputs, determining that the historical shopping activity indicates a first frequency of return transactions during the first time period;

determining that the recent shopping activity indicates a second frequency of return transactions during the second time period;

evaluating whether a second difference between the second frequency of return transactions and the first frequency of return transactions exceeds a second threshold value, as defined by R₂−

H₂>

T₂, where R₂ is the second frequency of return transactions, H₂ is the first frequency of return transactions, and T₂ is the second threshold value;

determining that the historical shopping activity indicates purchases among a first plurality of categories;

determining that the recent shopping activity indicates purchases among at least one second category;

evaluating whether the at least one second category belongs to one of the first plurality of categories;

determining that the historical shopping activity indicates online activity during the first time period from at least one of a first device, a first browser type, or a first internet protocol address;

determining that the recent shopping activity indicates online activity during the second time period from at least one of a second device, a second browser type, or a second internet protocol address;

evaluating a third difference between (i) the first device, the first browser type, or the first internet protocol address and (ii) the second device, the second browser type, or the second internet protocol address;

determining that the historical shopping activity indicates a first average credit per transaction during the first time period based on third party pricing data;

determining that the recent shopping activity indicates a second average credit per transaction during the second time period based on the third party pricing data; and

evaluating whether a fourth difference between the second average credit per transaction and the first average credit per transaction exceeds a third threshold value; and

when the difference between the recent shopping activity and the historical shopping activity indicates fraud, associated with transactions or return transactions, generating, by the fraud detection module, a flag with respect to the first transaction;

receiving, by the validation module, a validation decision;

when the validation decision indicates approval, crediting, by the validation module, an account associated with the user identifier with an amount corresponding to the one or more price differences;

when the validation decision indicates rejection, refraining from crediting the account associated with the user identifier with the amount corresponding to the one or more price differences;

when the difference between the recent shopping activity and the historical shopping activity does not indicate fraud, crediting the account associated with the user identifier with the amount corresponding to the one or more price differences;

when the difference between the recent shopping activity and the historical shopping activity does not indicate fraud and the validation decision indicates acceptance, perform at least one of;

(i) crediting the account associated with the user identifier with the amount corresponding to the one or more price differences, (ii) generating a redemption code having the amount corresponding to the one or more price differences and receive a request to redeem the redemption code from the user associated with the user identifier, or (iii) issuing a gift card to the user associated with the user identifier;

receiving transaction information related to a second transaction subsequent to the first transaction at the sale terminal;

transmitting an authorization to the sale terminal when the transaction information is valid, the authorization allowing the sale terminal to apply an amount to be credited to the second transaction subsequent to the first transaction; and

applying the amount of credit in the account associated with the user identifier toward a purchase price of the second transaction subsequent to the first transaction.

19. The method of claim 18, further comprising:

identifying a geographic location of the sale terminal at which the first transaction was concluded.

20. The method of claim 18, wherein the receiving of the record of the first transaction concluded on the sale terminal further comprises:

receiving, from a user computer, a transaction identifier.

21. The method of claim 18, wherein the evaluating whether a difference between the second average credit per transaction and the first average credit per transaction exceeds a third threshold condition indicates fraud, is defined by R₃−

H₃>

T₃, where R₃ is a recent return frequency, H₃ is a historical return frequency, and T₃ is the third threshold value.