Choosing a Digital Onboarding Solution


Digital onboarding is hot. As commerce and services continue their tectonic shift online, accelerated by the COVID pandemic, digital onboarding services are becoming the new gatekeepers. Recognizing the massive market opportunity, incumbents are consolidating and startups innovating. 

Digital onboarding brings together three intertwined aspects which need to be assessed when choosing an onboarding service:



Is a person who they say they are ? Traditionally this involves paperwork: utility bills, drivers licenses etc, verified in person. On the internet this doesn’t work. We can scan and send images online but how do we spot the old eyeball-on-a-pencil trick, making sure the flesh-and-bones matches paper-and-ink. As governments and issuing authorities move towards self-sovereign identities (SSI) stored in digital wallets, this problem will slowly disappear. In the interim, innovative computer vision solutions allow capture and comparison of document images and digital selfies, performing liveness checks using biometric markers. 

In addition to documents, onboarding services typically resolve consumer personal information (PII) independently through a variety of data vendors and check how well the results all fit together. Ongoing evaluation of data vendors and discovery of new uncorrelated data sources is an essential part of maintaining an accurate identity verification function. Fully-managed services like Instnt take care of this part for you, freeing businesses to focus on core competencies. In addition, Instnt augments PII data with behavioural biometrics, cohort analysis, and device fingerprinting captured from direct interaction with the consumer. This data is uncorrelated with PII and can offer measurable improvements in accuracy.


Fraud Risk

Fraudsters will use a combination of synthetic and hijacked identities to gain access to protected systems. Based on features described above, onboarding services will make an assessment of the likelihood of a consumer to commit fraud. Rule-based assessments tend to be less accurate than those based on trained models which optimize outcomes based on historical data and can be easily re-trained as data and behaviours evolve. Instnt employs multiple predictive models, each trained specifically to deal with different modes of fraud and regularly updated to keep pace with changing behaviours and demographics.

Typically fraud assessments are a binary YES or NO. Instnt generates a Level-of-Assurance (LOA) based on the strength of evidence provided by the subject. These levels are aligned with NIST categorization employed by SSI governance frameworks and allow a more nuanced approach to onboarding whereby loan or credit limits can be indexed to the LOA for example. 



Fully-managed onboarding services that have complete control of data sources and predictive models are able to indemnify fraud loss. Instnt offers up to $100M in aggregate fraud loss coverage and enables financial institutions to reduce counterparty risk, lowering capital requirements under Dodd-Frank and Basel III regulations. 

Under the US Patriot Act and Canada’s PCMLTFA, financial service providers are required by law to take measures to combat terrorism financing and other financial crimes. These know-your-customer (KYC) and anti-money-laundering (AML) measures are prescriptive in terms of required proof of identification and the checks that must be performed to determine the global standing of individuals and companies. Violation of these rules has serious consequences for company executives and an onboarding service that performs these checks should be carefully vetted to ensure that it satisfies all regulations and audit trails to support investigation. 



In the past main-street businesses would focus on the store front, attractive signage, and free hot-dogs to attract customers. Digital onboarding is the new store front: too much friction and customers just keep walking while a lack of diligence burns a hole in your pocket. Picking the right onboarding service is about finding a healthy tension between forces that drives top-line growth without hurting the bottom line. Onboarding services must have coverage on the target market and not be biased against thin-file consumers like Millennials and new immigrants. It’s a competitive landscape out there and no business can afford to shut out fast growing sectors of the population, especially one predicted to inherit over  $24 trillion in transferred wealth over the next 15 year in the US alone.

For more on improving your digital onboarding read 7 Reasons Why Your Company Needs Digital Customer Onboarding. 



About the Author

Justin is the Chief Product Officer at Instnt. He has over 20 years experience designing and building high performance distributed systems in the telecommunications, IPTV, identity verification, social media analytics, and IIoT industries. He holds patents in computer vision and collaborative filtering. He has leveraged his technical and quantitative background to deliver AI-driven solutions at Salesforce, Alcatel-Lucent, and Bell Canada, in North America, Europe, and Africa. Justin holds a degree in mechanical engineering from University of the Witwatersrand, South Africa, as well as MS in computer science and mathematics from University of New Brunswick, Canada.