OCR Labs’ liveness detection software shows zero demographic bias and its results are 100 per cent accurate; new independent testing confirms.
The identity verification software company OCR Labs Global recently submitted its liveness detection software for evaluation. The testing, which was conducted by the independent biometric testing laboratory BixeLab, was to determine how much bias the software incurs in its analysis of race, age and gender.
For this reason, the laboratory considered male, female and transgender candidates, aged 18 to 70, from eight ethnic groupings in its evaluation.
The recently-published results confirm the total impartiality of OCR Labs’ software, which scored zero per cent in demographic bias and zero per cent in error rates.
However, identity verification continues to face a major challenge in human decision-making in screening, as studies have revealed that it leads to higher rates of exclusion for non-white, female, and non-primary language individuals.
Corresponding research from MIT confirms this flaw, as its data shows women and ethnic minorities are most at risk from the failure to build inclusive digital identity solutions, as leading facial recognition systems worked at a 0.8 per cent error rate for white men but had a 34.7 per cent error rate for dark-skinned women.
For this reason, OCR Labs’ liveness detection software leverages a deep neural network to overcome this bias. In this way, the power to support underserved groups in society is being realised through the application of inclusive digital identity systems.
The role of digital ID systems in achieving financial inclusion
By removing barriers that lead to exclusion, digital ID systems, like that of OCR Labs, can ensure that as many people as possible have access to crucial products and services such as banking or recruitment, irrespective of their native background or appearance; as Russ Cohn, general manager international for OCR Labs Global, explains.
“We believe that by removing barriers that lead to exclusion, digital ID systems can ensure that as many people as possible have access to life-enhancing products and services, no matter their background,” comments Cohn. “The time has come to refocus efforts on achieving inclusivity to prepare for the future when more people than ever will use identity solutions.”
The company is actively preparing for this more inclusive future with the application of its zero-bias artificial intelligence (AI), consumer education and the use of partnerships with companies like Bloom Money, Reed Screening and Admiral Money.
“Using our technology, Bloom Money helps diaspora communities across Europe manage their finances seamlessly through their app, overcoming data bias,” Cohn explains. “Likewise, Reed Screening is actively tackling manual screening bias using our software to make hiring faster, fairer and safer.
“Admiral Money is utilising our solution and research…to facilitate access to home improvement loans, debt consolidation and car financing products to traditionally underserved groups that speak, read and write multiple languages,” he concludes.
Identity stories whitepaper
To help companies understand the value of prioritising inclusion when building identity systems, OCR Labs Global is releasing a whitepaper on ‘Identity Stories: The Truths About Identity and Inclusion’.
The whitepaper covers the main challenges of inclusive digital identity systems and provides guidelines for companies to address specific systemic biases and build inclusive systems.