Risk assessment framework for identity verification system

A system comprising:

• a sensor device configured to record characteristic data describing actions of a requesting target user;
• a computing device communicatively coupled to the sensor device, wherein the computing device is configured to grant access to the requesting target user;
• and
• a non-transitory computer-readable medium comprising stored computer-readable instructions that, when executed by one or more processors, cause the one or more processors to:
• receive a request from a requesting target user for access to an operational context, wherein the request comprises authentication credentials representing an authenticating identity;
• access a match probability for the requesting target user, wherein the match probability represents a likelihood that the identity of the requesting target user matches the authenticating identity determined using an identity confidence model;
• determine a false match rate and a false non-match rate for the identity confidence model;
• determine a decayed false match rate and a decayed non-false match rate by applying a decay parameter to decay each of the false match rate and the false non-match rate as a function of time;
• update the match probability over a time period based on the decayed false match rate and decayed non-false match rate at corresponding times during the time period;
• and
• grant the requesting target user access to the operational context during the time period until the match probability is less than an operational security threshold.

A method comprising:

• receiving a request from a requesting target user for access to an operational context, wherein the request comprises authentication credentials representing an authenticating identity;
• accessing a match probability for the requesting target user, wherein the match probability represents a likelihood that the identity of the requesting target user matches the authenticating identity determined using an identity confidence model;
• determining a false match rate and a false non-match rate for the identity confidence model;
• determining a decayed false match rate and a decayed non-false match rate by applying a decay parameter to decay each of the false match rate and the false non-match rate as a function of time;
• updating the match probability over a time period based on the decayed false match rate and decayed non-false match rate at corresponding times during the time period;
• and
• granting the requesting target user access to the operational context during the time period until the match probability is less than an operational security threshold.