What are confidence values?

Smile ID applies an ensemble of facial verification algorithms designed to compare and predict potential matches of faces regardless of their expression, facial hair, and age.

Our service provides an estimate of the confidence level of the prediction in the form of a probability or Confidence Value.

Smile ID has a confidence value between 0% and 100%, the higher the number, the more confident the system is about the match. The confidence score is an indication of the probability of us returning a false match/FAR (False Acceptance Rate). Smile ID works with its partners to identity the specific use case and desired risk profile to set confidence score thresholds. The acceptance or rejection of a facial match is dependent on the score falling above or below the set threshold.

As a guideline: Lower thresholds reduce the restrictions when evaluating results, this means jobs that would have failed at a higher threshold would now pass resulting in more jobs accepted.

The risk of more false matches/FAR (False Acceptance Rate) are more suited for business non-critical use cases where there is lower risk. Higher thresholds are more critical which means fewer jobs make it through. Higher thresholds are suitable for business-critical uses cases such as high value or sensitive transactions.