Dynamic fraud intervention machine

Abstract

A machine detects a request to execute a transaction specified by a first set of user inputs. The machine determines, based on the first set of user inputs that specified the transaction, that the request to execute the transaction is to be verified with a corresponding challenge prompt that is to be generated for the request to execute the transaction. The machine then generates the challenge prompt that corresponds to the request to execute the transaction specified by the first set of user inputs that specified the transaction, and the machine causes presentation of the generated challenge prompt that corresponds to the request to execute the transaction. In response to the presented challenge prompt, the machine may receive a second set of user inputs. Based on the second set of user inputs, the machine then generates an indication of whether the request is verified.

What is claimed is: 
     
         1 . A method comprising:
 detecting, by one or more processors, a request to initiate a transaction specified by first inputs from a user;   determining, by the one or more processors, a fraud likelihood score of the request based on the first inputs that specified the transaction;   generating, by the one or more processors and based on the fraud likelihood score of the request, a challenge prompt to verify the request;   receiving, by the one or more processors, second inputs from the user in response to a presentation of the challenge prompt generated based on the fraud likelihood score of the request; and   generating, by the one or more processors, an indication of whether the request to initiate the transaction is verified based on the second inputs received in response to the presentation of the challenge prompt.   
     
     
         2 . The method of  claim 1 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a determination that the fraud likelihood score of the request is in a first range of fraud likelihood scores between a second range of fraud likelihood scores and a third range of fraud likelihood scores, the second range corresponding to presence of fraud and the third range corresponding to absence of fraud.   
     
     
         3 . The method of  claim 1 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a comparison of the first inputs to reference inputs that indicate coercion;   the generated challenge prompt is configured to trigger behavior indicative of coercion; and   the generating of the indication is based on whether the behavior indicative of coercion is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         4 . The method of  claim 1 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a comparison of the first inputs to reference inputs that indicate coaching;   the generated challenge prompt is configured to trigger behavior indicative of coaching; and   the generating of the indication is based on whether the behavior indicative of coaching is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         5 . The method of  claim 1 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a detection of a detected handedness of the user based on the first inputs;   the generated challenge prompt requests submission of hand inputs that indicate a reference handedness of the user; and   the generating of the indication is based on whether the hand inputs that indicate the reference handedness of the user are included in the second inputs received in response to the generated challenge prompt.   
     
     
         6 . The method of  claim 1 , wherein:
 the first inputs that specified the transaction indicate a detected completion time to enter an entered text phrase;   the generated challenge prompt requests entry of a reference text phrase; and   the generating of the indication is based on whether a reference completion time to enter the reference text phrase is transgressed by the second inputs received in response to the generated challenge prompt.   
     
     
         7 . The method of  claim 1 , wherein:
 the first inputs that specified the transaction indicate a detected combination of input cadence and input error rate to enter an entered text phrase;   the generated challenge prompt requests entry of a reference text phrase; and   the generating of the indication is based on whether a reference combination of input cadence and input error rate is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         8 . A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:
 detecting a request to initiate a transaction specified by first inputs from a user;   determining a fraud likelihood score of the request based on the first inputs that specified the transaction;   generating, based on the fraud likelihood score of the request, a challenge prompt to verify the request;   receiving second inputs from the user in response to a presentation of the challenge prompt generated based on the fraud likelihood score of the request; and   generating an indication of whether the request to initiate the transaction is verified based on the second inputs received in response to the presentation of the challenge prompt.   
     
     
         9 . The non-transitory machine-readable storage medium of  claim 8 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a determination that the fraud likelihood score of the request is in a first range of fraud likelihood scores between a second range of fraud likelihood scores and a third range of fraud likelihood scores, the second range corresponding to presence of fraud and the third range corresponding to absence of fraud.   
     
     
         10 . The non-transitory machine-readable storage medium of  claim 8 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a comparison of the first inputs to reference inputs that indicate coercion;   the generated challenge prompt is configured to trigger behavior indicative of coercion; and   the generating of the indication is based on whether the behavior indicative of coercion is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         11 . The non-transitory machine-readable storage medium of  claim 8 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a comparison of the first inputs to reference inputs that indicate coaching;   the generated challenge prompt is configured to trigger behavior indicative of coaching; and   the generating of the indication is based on whether the behavior indicative of coaching is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         12 . The non-transitory machine-readable storage medium of  claim 8 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a detection of a detected handedness of the user based on the first inputs;   the generated challenge prompt requests submission of hand inputs that indicate a reference handedness of the user; and   the generating of the indication is based on whether the hand inputs that indicate the reference handedness of the user are included in the second inputs received in response to the generated challenge prompt.   
     
     
         13 . The non-transitory machine-readable storage medium of  claim 8 , wherein:
 the first inputs that specified the transaction indicate a detected completion time to enter an entered text phrase;   the generated challenge prompt requests entry of a reference text phrase; and   the generating of the indication is based on whether a reference completion time to enter the reference text phrase is transgressed by the second inputs received in response to the generated challenge prompt.   
     
     
         14 . The non-transitory machine-readable storage medium of  claim 8 , wherein:
 the first inputs that specified the transaction indicate a detected combination of input cadence and input error rate to enter an entered text phrase;   the generated challenge prompt requests entry of a reference text phrase; and   the generating of the indication is based on whether a reference combination of input cadence and input error rate is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         15 . A system comprising:
 one or more processors; and   a memory storing instructions that, when executed by at least one processor among the one or more processors, cause the system to perform operations comprising:   detecting a request to initiate a transaction specified by first inputs from a user;   determining a fraud likelihood score of the request based on the first inputs that specified the transaction;   generating, based on the fraud likelihood score of the request, a challenge prompt to verify the request;   receiving second inputs from the user in response to a presentation of the challenge prompt generated based on the fraud likelihood score of the request; and   generating an indication of whether the request to initiate the transaction is verified based on the second inputs received in response to the presentation of the challenge prompt.   
     
     
         16 . The system of  claim 15 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a determination that the fraud likelihood score of the request is in a first range of fraud likelihood scores between a second range of fraud likelihood scores and a third range of fraud likelihood scores, the second range corresponding to presence of fraud and the third range corresponding to absence of fraud.   
     
     
         17 . The system of  claim 15 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a comparison of the first inputs to reference inputs that indicate coercion;   the generated challenge prompt is configured to trigger behavior indicative of coercion; and   the generating of the indication is based on whether the behavior indicative of coercion is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         18 . The system of  claim 15 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a comparison of the first inputs to reference inputs that indicate coaching;   the generated challenge prompt is configured to trigger behavior indicative of coaching; and   the generating of the indication is based on whether the behavior indicative of coaching is indicated by the second inputs received in response to the generated challenge prompt.   
     
     
         19 . The system of  claim 15 , wherein:
 the generating of the challenge prompt to verify the request is responsive to a detection of a detected handedness of the user based on the first inputs;   the generated challenge prompt requests submission of hand inputs that indicate a reference handedness of the user; and   the generating of the indication is based on whether the hand inputs that indicate the reference handedness of the user are included in the second inputs received in response to the generated challenge prompt.   
     
     
         20 . The system of  claim 15 , wherein:
 the first inputs that specified the transaction indicate a detected completion time to enter an entered text phrase;   the generated challenge prompt requests entry of a reference text phrase; and   the generating of the indication is based on whether a reference completion time to enter the reference text phrase is transgressed by the second inputs received in response to the generated challenge prompt.