Systems and methods for fraud prevention in mobile application verification device enrollment process
Systems and methods are directed to an improved fraud detection feature in Mobile Application Verification (MAV) device enrollment process. The proposed solution corresponds to a two-prong approach involving a strength factor evaluation of the authentication inputs provided during the initial enrollment process, and a computation of a number of trust parameters values from archived transactional records. A computational model supplemented with a machine learning process is then used to determine a device stability period as a function of the strength factor associated with the user provided authentication data and the computed trust factors.
1 . A method for optimizing probability of valid device enrollment performed by a computer hardware arrangement, the method comprising:
determining a device identifier for a transmitting device in response to a mobile application verification (MAV) enrollment request initiated by the transmitting device, the enrollment request being associated with a user account;
initiating a device stability waiting period upon verifying one or more authentication credentials provided by the transmitting device, the one or more authentication credentials being associated with the user account;
verifying a strength factor associated with the one or more authentication credentials, wherein the device stability waiting period, is a decreasing function of the strength factor;
applying a computational model to determine a length of the device stability waiting period as a function of the strength factor;
retrieving a value for one or more trust parameters based on historical records associated with the user account and the transmitting device, the one or more trust parameters comprising:
a number previous authentication requests associated with one or more of the transmitting device and the user account,
a number of previous successful challenges associated with one or more of the transmitting device and the user account, and
a period of time elapsed since a most recent successful challenge associated with one or more of the transmitting device and the user account;
determining a scaling factor for each of the one or more trust parameters using a machine learning process, wherein the value for each of the one or more trust parameters is scaled based on a corresponding scale factor, thereby generating one or more scaled values;
inputting the one or more scaled values into the computational model for modifying the length of the device waiting period based on the one or more scaled values; and
generating a fraud probability value for the MAV enrollment request initiated by the transmitting device, wherein the fraud probability value is directly proportional to the device stability waiting period.
2 . The method of claim 1 , wherein the verifying a strength factor of the one or more authentication credentials corresponds to determining whether the one or more authentication credentials corresponds to at least one selected from a group of a short message service (SMS) message, a user password and a contactless card one-time password (OTP) authentication.
3 . The method of claim 1 , wherein the one or more trust parameters further comprise a number of previous authentication requests associated with the user account that were initiated by the transmitting device.
4 . The method of claim 1 , where the one or more trust parameters further comprise a number of previous successful challenges associated with the user account that were initiated by the transmitting device.
5 . The method of claim 1 , wherein the value for a trust parameter, corresponding to the number of previous successful challenges, is scaled based on a strength factor associated with each of the previous successful challenges.
6 . The method of claim 1 , further comprising capturing device specific data from the transmitting device, wherein the device specific data comprises a malware presence and a device fingerprint.
7 . The method of claim 1 , wherein a fraud probability value above a predetermined threshold value indicates ineligibility of the transmitting device for the MAV enrollment.
8 . The method of claim 1 , wherein the number of previous authentication requests initiated by the transmitting device is determined based on a predetermined period of time.
9 . The method of claim 1 , wherein the number of previous authentication requests associated with the user account is determined based on a predetermined period of time.
10 . The method of claim 1 , wherein the value for each of the one or more trust parameters associated with the number of previous successful challenges is scaled based on an authentication strength factor associated with each of the previous successful challenges.
11 . The method of claim 1 , wherein the machine learning process is trained based on a plurality of user fraud reports associated with a plurality of user accounts.
12 . A system for optimizing valid device enrollment, the system comprising a computer hardware arrangement configured to:
determine a device identifier for a transmitting device in response to a mobile application verification (MAV) enrollment request initiated by the transmitting device, the MAV enrollment request being associated with a user account;
initiate a device stability waiting period upon verifying one or more authentication credentials provided by the transmitting device, the one or more authentication credentials being associated with the user account;
verify a strength factor associated with the one or more authentication credentials, wherein the device stability waiting period is a decreasing function of the strength factor;
apply a computational model to determine a length of the device stability waiting period as a function of the strength factor;
retrieve a value for one or more trust parameters based on historical records associated with the user account and the transmitting device, the one or more trust parameters comprising:
a number of previous authentication requests associated with one or more of the transmitting device and the user account;
a number of previous successful challenges associated with one or more of the transmitting device and the user account; and
a period of time elapsed since a most recent successful challenge associated with one or more of the transmitting device and the user account;
determine a scaling factor for each of the one or more trust parameters using a machine learning process, wherein the value for each of the one or more trust parameters is scaled based on a corresponding scale factor, thereby generating one or more scaled values;
input the one or more scaled values into the computational model to modify the length of the device stability waiting period based on the one or more scaled values; and
generate a fraud probability value for the MAV enrollment request initiated by the transmitting device, wherein the fraud probability value is directly proportional to the device stability waiting period.
13 . The system of claim 12 , wherein the one or more trust parameters further comprise a number of previous authentication requests associated with the user account that were initiated by the transmitting device.
14 . The system of claim 12 , wherein the value for a trust parameter, corresponding to the number of previous successful challenges, is scaled based on a strength factor associated with each of the previous successful challenges.
15 . The system of claim 12 , wherein the computer hardware arrangement is further configured to generate a device ineligibility notification in response to a fraud probability value that is above a predetermined threshold.
16 . The system of claim 12 , wherein the computer hardware arrangement is further configured to scale the value for each of the one or more trust parameters associated with the number of previous successful challenges, based on a strength factor associated with each of the previous successful challenges.
17 . The system of claim 12 , wherein the computer hardware arrangement is further configured to train the machine learning process based on a plurality of user fraud reports associated with a plurality of user accounts.
18 . A non-transitory computer-accessible medium comprising instructions for execution by a computer hardware arrangement, wherein, upon execution of the instructions the computer hardware arrangement is configured to perform procedures comprising:
determining a device identifier for a transmitting device in response to a mobile application verification (MAV) enrollment request initiated by the transmitting device, the enrollment request being associated with a user account;
initiating a device stability waiting period upon verifying one or more authentication credentials provided by the transmitting device, the one or more authentication credentials being associated with the user account;
verifying a strength factor associated with the one or more authentication credentials, wherein the device stability waiting period, is a decreasing function of the strength factor;
applying a computational model to determine a length of the device stability waiting period as a function of the strength factor;
retrieving a value for one or more trust parameters based on historical records associated with the user account and the transmitting device, the one or more trust parameters comprising:
a number previous authentication requests associated with one or more of the transmitting device and the user account,
a number of previous successful challenges associated with one or more of the transmitting device and the user account, and
a period of time elapsed since a most recent successful challenge associated with one or more of the transmitting device and the user account;
determining a scaling factor for each of the one or more trust parameters using a machine learning process, wherein the value for each of the one or more trust parameters is scaled based on a corresponding scale factor, thereby generating one or more scaled values;
inputting the one or more scaled values into the computational model for modifying the length of the device stability waiting period based on the one or more scaled values; and
generating a fraud probability value for the MAV enrollment request initiated by the transmitting device, wherein the fraud probability value is directly proportional to the device stability waiting period.
19 . The non-transitory computer-accessible medium of claim 18 , further comprising instructions for scaling the value of a trust parameter, corresponding to the number of previous successful challenges, based on a strength factor associated with each of the previous successful challenges.
20 . The non-transitory computer-accessible medium of claim 18 , further comprising instructions for training the machine learning process based on a plurality of user fraud reports associated with a plurality of user accounts.