Blog Posts

August 23, 2022

Introducing the First Episode 1 of Under The Hood Season 2

Carla McMorris
Director of Content

Click here to listen to the full podcast.

Announcing season 2 of Under The Hood. In this newly released season, we will explore topics that range from design and architecture to regulatory and policy challenges. 

In Episode 1, Sankaet Pathak, CEO, Synapse will discuss how identity, fraud, and AML solutions are built, how they work and how they don’t, and what changes need to be made for hyperscale. Sankaet will be joined by Hrishi Dixit, CTO of Yieldstreet. Headquartered in New York, Yieldstreet provides investment opportunities for retail investors, and everyday people, to invest in products outside of the public markets, like real estate. To provide the service, Yieldstreeet needs to move money, people need to open accounts, and people need to move money to the platform and deploy that to investments.

Sankaet and Hrishi covered a lot of ground in this episode. Here are the high points:

How do you conduct identity verification without losing the customer?

When a user encounters a wall their first instinct is to say “oh, forget this”, but this is a critical point in the journey. Sankaet shared there is identity verification that is just about regulatory compliance, and there is another side that’s all about protecting the customer. 

“How do we build an experience that is (a) delight, that is smooth, that is (I) dare say enjoyable while at the same time, keeping our investors and us safe?”

Is a one point and time check on identity enough?

The unfortunate reality of identity is identity theft. Sankaet offered a series of solutions that begins with what the regulators ask for as a bare minimum, then move on to an architecturally built system based on how much information you have on the user (low, medium and high), and finally have a different system which is based on their engagement with their account on the platform. 

“Can we faithfully answer the question that a person deemed as safe or trustworthy at a point in time continues to retain that trust level downstream?”

Can the identity problem be generalized or does it have to be specialized?

Hrishi believes that there is a substrate that can be generalized, but beyond that, it needs to be a function of the specific business. Sankaet believes that identity can be generalized as a snapshot, but continuous trust needs also to be local to detect some patterns that are just blatantly strange.

“For a fraud model that has some basic templates, maybe, some axiomatic elements that are portable, that are generalizable, but then beyond that, you're learning about our business.” 

Are there architectural solutions that are superior regarding identity?

Ultimately there’s no exact architectural solution. What model or models give you the highest confidence level? The confidence level can only be partly solved architecturally, the real thing is where is the richest source of data that can actually drive these models.

 

“Because there's any number of modelists that can do this well, but they're useless unless you have like a massive, massive corpus to dip into.“

Can you architect a KYC, or identity verification or fraud and still meet the speed expectations of retail consumers? 

Sankaet highlighted that shallow models and then deep models work well for a good user, but for a bad user, the experience would not be instantaneous because they will get approved and then rejected. Hrishi explained that one of the ways Yieldstreet meets the speed expectation is by restricting the lanes of the consumer. There’s also the safe amount concept for instantly authorizing transactions based on known history.

“...you are simulating instantaneous behavior in many cases (but) you're actually doing it right away.”

How do ID Score and Fraud Score work?

ID Score helps to verify the likelihood of identity and Fraud Score is the ongoing engine for transaction activity. 

“Our customers can hijack the global rules with local rules that are much more nuanced and specialized to their personal vertical.”

Envisioning a Federated Identity System

Sankaet envisions a consortium of platforms that safely share global identities, and can be shared across multiple SaaS platforms and their customers. The vision is to be able to bring onboarding into a financial ecosystem as close to a social network as you can, because if you build a federated identity, you can then build authentication, then port information from one platform to another.

 

“This is one of the biggest values that you (Synapse), as a Banking as a Service platform that has the benefit of building to a picture of a user from multiple tenancies and tying them together.” 

The Importance of Reliable AML Practices

Hrishi explains how important it is to go through not just KYC and fraud, but also real AML and OFAC background screening of every investor on their platform. 

“...we have this added layer of faith and trust that we need to demonstrate, not just to the auditors, but also to our counterparties and the partners that we work with on the other side of the marketplace who are looking to put their product on our platform, right?”

Sources

Introducing the First Episode 1 of Under The Hood Season 2

< Back
Carla McMorris
August 23, 2022

What’s a Rich Text element?

The rich text element allows you to create and format headings, paragraphs, blockquotes, images, and video all in one place instead of having to add and format them individually. Just double-click and easily create content.

Static and dynamic content editing

A rich text element can be used with static or dynamic content. For static content, just drop it into any page and begin editing. For dynamic content, add a rich text field to any collection and then connect a rich text element to that field in the settings panel. Voila!

How to customize formatting for each rich text

Headings, paragraphs, blockquotes, figures, images, and figure captions can all be styled after a class is added to the rich text element using the "When inside of" nested selector system.