SYSTEM AND METHOD FOR EVALUATING RISK IN FRAUD PREVENTION

• US 20120030083A1
• Filed: 04/12/2011
• Published: 02/02/2012
• Est. Priority Date: 04/12/2010
• Status: Active Grant

• Current Assignee: iovation Incorporated
• Original Assignee: iovation Incorporated
• Inventors: Lonchar, Bart, Newman, Jim, Waddell, Scott
• Granted Patent: US 8,676,684 B2
• Time in Patent Office: Days
• US Class Current: 705/35
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 40/02 Banking, e.g. interest calculation or account maintenance credit or loans G06Q40/03

Abstract

A method of determining a risk score indicating a risk that an electronic transaction will involve fraud and/or abuse. The method includes receiving transaction data associated with a not yet completed transaction from a merchant. The transaction data includes one or more characteristics related to the transaction. A profile is selected that identifies network devices each associated with the characteristics and having a device reputation. Next, a profile-based risk factor is determined as a function of a percentage of the network devices having a negative reputation. The risk score is determined as a function of the profile-based risk factor. In some embodiments, a transaction-based risk factor may also be determined. In such embodiments, the risk score is determined as a function of the profile-based and transaction-based risk factors. The risk score is provided to the merchant to be used thereby to determine whether to proceed with the transaction.

Claims

1. A computer-implemented method executable by one or more computing devices, the method being for use with a merchant, the method comprising:

receiving transaction data associated with a not yet completed transaction from the merchant, the transaction data comprising one or more first characteristics related to the transaction;

selecting a profile identifying a plurality of network devices each associated with the one or more first characteristics, each of the plurality of network devices being associated with a reputation;

determining a profile-based risk factor as a function of a percentage of the plurality of network devices of the profile having a negative reputation;

determining a risk score as a function of the profile-based risk factor; and

providing the risk score to the merchant to be used thereby to determine whether to proceed with the transaction.

2. The method of claim 1, wherein the one or more first characteristics comprise at least one of an Internet Protocol address associated with a customer device conducting the not yet completed transaction with the merchant, a property of the customer device, a geographic location of the customer device, an account identifier associated with the customer device, a country associated with the customer device, and a language associated with the customer device.

3. The method of claim 1 for use with a plurality of subscribers comprising the merchant, the method further comprising:

receiving transaction data related to a plurality of past transactions conducted by the plurality of subscribers with the plurality of network devices, for each of the plurality of past transactions, the transaction data comprising an indication of whether the past transaction involved fraud; and

determining the reputations of the plurality of network devices based on the transaction data related to the plurality of past transactions.

4. The method of claim 2, further comprising:

receiving a request from the merchant for a portion of the transaction data related to the plurality of past transactions; and

providing the portion of the transaction data to the merchant in response to the request.

5. The method of claim 1, wherein the risk score is determined as a function of the profile-based risk factor and a weighting factor.

6. The method of claim 4, wherein the weighting factor is provided by the merchant.

7. The method of claim 1, further comprising:

determining a weighted profile-based risk factor as a function of the profile-based risk factor and a weighting factor, wherein the risk score is determined as a function of a product of a scaling factor and a square of the logarithm of the weighted profile-based risk factor.

8. The method of claim 1, further comprising:

selecting a transaction-based risk factor comprising one or more second characteristics and a weight, wherein if the transaction data includes the one or more second characteristics, the risk score is determined as a function of the profile-based risk factor and the weight of the transaction-based risk factor.

9. The method of claim 8 for use with a plurality of subscribers comprising the merchant, the method further comprising:

receiving transaction data related to a plurality of past transactions conducted by the plurality of subscribers with the plurality of network devices, for each of the plurality of past transactions, the transaction data comprising an indication of whether the past transaction involved fraud;

determining the reputations of the plurality of network devices based on the transaction data related to the plurality of past transactions; and

determining a first number of the plurality of network devices that conducted one or more of the plurality of past transactions in which the transaction-based risk factor was present;

determining a second number of the first number of the plurality of network devices having a negative reputation; and

determining the weight of the transaction-based risk factor as a function of the first and second numbers.

10. The method of claim 1 for use with a plurality of subscribers comprising the merchant, the method further comprising:

receiving transaction data related to a plurality of past transactions conducted by the plurality of subscribers with the plurality of network devices, for each of the plurality of past transactions, the transaction data comprising an indication of whether the past transaction involved fraud;

identifying a transaction-based risk factor and a weight based on the transaction data related to the plurality of past transactions, the weight indicating a level of risk associated with a transaction for which the transaction-based risk factor is present;

after determining the transaction-based risk factor is present in the transaction data associated with the not yet completed transaction, determining a transaction-based risk score as a function of the weight; and

determining a profile-based risk score as a function of the profile-based risk factor, wherein the risk score is determined as a function of the profile-based risk score and the transaction-based risk score.

11. The method of claim 1, further comprising:

determining a weighted profile-based risk factor as a function of the profile-based risk factor and a weighting factor;

determining a profile-based risk score as a product of a scaling factor and a square of the logarithm of the weighted profile-based risk factor;

selecting a transaction-based risk factor comprising one or more second characteristics and a weight; and

after determining the transaction data includes the one or more second characteristics, determining a weighted transaction-based risk factor as a function of the weight, and determining a transaction-based risk score as a product of the scaling factor and a square of the logarithm of the weighted transaction-based risk factor, wherein the risk score is determined as a function of the profile-based risk score and the transaction-based risk score.

12. The method of claim 1, further comprising:

if the transaction data does not include the one or more second characteristics, determining the transaction-based risk score is zero.

13. The method of claim 1, wherein determining the percentage of the plurality of network devices of the profile having a negative reputation comprises determining for each of the plurality of network devices, whether the reputation associated with the network device is negative according to criteria specified by the merchant.

14. A computer-implemented method executable by one or more computing devices, the method being for use with a merchant, the method comprising:

receiving transaction data associated with a not yet completed transaction from the merchant, the transaction data comprising one or more first characteristics related to the transaction;

selecting a plurality of profiles each identifying at least a portion of the one or more first characteristics;

for each of the plurality of profiles, identifying a plurality of network devices each associated with the portion of the one or more first characteristics identified by the profile, each of the plurality of network devices being associated with a reputation;

for each of the plurality of profiles, determining a profile-based risk factor as a function of a percentage of the plurality of network devices identified for the profile having a negative reputation;

determining a risk score as a function of the profile-based risk factors determined for the plurality of profiles; and

providing the risk score to the merchant to be used thereby to determine whether to proceed with the transaction.

15. The method of claim 14 for use with a plurality of subscribers comprising the merchant, the method further comprising:

receiving transaction data related to a plurality of past transactions conducted by the plurality of subscribers with the plurality of network devices identified for the plurality of profiles, for each of the plurality of past transactions, the transaction data comprising an indication of whether the past transaction involved at least one of fraud and abuse; and

determining the reputations of the plurality of network devices identified for the plurality of profiles based on the transaction data related to the plurality of past transactions.

16. The method of claim 15, further comprising:

identifying a transaction-based risk factor and a weight based on the transaction data related to the plurality of past transactions, the weight indicating a level of risk associated with a transaction for which the transaction-based risk factor is present;

after determining the transaction-based risk factor is present in the transaction data associated with the not yet completed transaction, determining a transaction-based risk score as a function of the weight; and

determining a profile-based risk score as a function of the profile-based risk factor, wherein the risk score is determined as a function of the profile-based risk score and the transaction-based risk score.

17. The method of claim 16, further comprising:

receiving a request from the merchant for a portion of the transaction data related to the plurality of past transactions; and

providing the portion of the transaction data to the merchant in response to the request.

18. The method of claim 14, wherein the risk score is determined as a function of each of the profile-based risk factors multiplied by an associated weighting factor.

19. The method of claim 14, further comprising:

determining a weighted profile-based risk factor by summing products of each of the profile-based risk factors and an associated weighting factor, wherein the risk score is determined as a function of a product of a scaling factor and a square of the logarithm of the weighted profile-based risk factor.

20. The method of claim 14, further comprising:

determining a weighted profile-based risk factor by summing products of each of the profile-based risk factors and an associated weighting factor;

determining a profile-based risk score as a product of a scaling factor and a square of the logarithm of the weighted profile-based risk factor;

selecting a plurality of transaction-based risk factors each comprising one or more second characteristics and a weight; and

identifying ones of the plurality of transaction-based risk factors for which the transaction data includes the one or more second characteristics;

determining a weighted transaction-based risk factor by summing products of the weight of each of the identified ones of the plurality of transaction-based risk factors and an associated weighting factor; and

determining a transaction-based risk score as a product of the scaling factor and a square of the logarithm of the weighted transaction-based risk factor, wherein the risk score is determined as a function of the profile-based risk score and the transaction-based risk score.

21. A method for use with a database storing transaction data related to a plurality of past transactions between a plurality of network devices and a plurality of merchants, each of the plurality of network devices being associated with a device identifier, the method comprising:

identifying as fraudulent devices ones of the plurality of network devices associated with fraudulent or abusive transactions in the transaction data;

associating a negative reputation with each of the fraudulent devices;

identifying characteristics common to the fraudulent devices;

constructing a plurality of profiles based on the identified characteristics, each of the profiles comprising one or more of the identified characteristics;

receiving new transaction data associated with a not yet completed transaction;

for each of the plurality of profiles, identifying a value for each of the one or more identified characteristics of the profile included in the new transaction data;

for each of the plurality of profiles, identifying as belonging to the profile ones of the plurality of network devices associated with the value identified for each of the one or more identified characteristics of the profile;

for each of the plurality of profiles, determining a portion of the ones of the plurality of network devices that belong to the profile that are fraudulent devices; and

constructing a risk score based at least in part on the portion of the ones of the plurality of network devices that belong to each of the profiles that are fraudulent devices.