ID Score
id_score
Feature in Closed Beta
This new feature is currently being tested and improved. We prefer to keep some details about it private, as they are subject to change. Due the nascency of closed beta offerings, we cannot provide the same SLA guarantees of our released features.
Introduction
Fraudulent, stolen, and synthetic identities are a few of the biggest problems the financial industry faces today. To help prevent these from occurring in Synapse’s ecosystem, Synapse has created a new identity verification product, ID Score. ID Score is built on the idea that well-intended nded individuals leave behind “digital breadcrumbs” as they go about their lives, creating a robust tapestry of contact, social, and demographic information. On the other hand, fraudulent or synthetic identities only have limited or inconsistent information. Synapse uses these “digital breadcrumbs” that everyone leaves behind to determine Synapse's confidence level that a user is who they purport to be.
Product Overview
After document submission, we return an associated ID Score (id_score), a weighted numerical score indicating our relative confidence in the captured KYC (i.e. that the user is who they claim to be). Based on this determination, Synapse can request appropriate additional documentation, to be verified by Synapse’s identity verification tools, and prioritize manual review of users flagged for higher risk of fraudulent identity. ID Score is a tool intended to determine whether to request additional documentation from the user for Synapse to review.
- Please note that ID Score is not an indicator of the user’s trustworthiness or likelihood to commit fraud, and should not impact how the user is treated or how the Platform classifies the user.
Features
At the beginning of the user onboarding process, nearly every end-user submits the following data points to Synapse:
- Name
- Physical address
- Email address
- Phone number
- IP address
- Date of Birth (DOB)
Synapse then evaluates this submitted data. For example, Synapse will place additional scrutiny (including restrictions) on IP addresses associated with:
- Known web crawlers
- VPN proxies
- Anonymity networks (e.g. Tor)
Sometimes our model will need to account for user-submitted information that may not necessarily be an indicator of fraud. To delve deeper into a location example, a user may submit a phone number with a 415 area code (i.e. associated with the San Francisco Bay Area) while listing a current address in Los Angeles--and our model may be able to disregard the location mismatch if we can find evidence of previous San Francisco residency in their address history and we can independently verify that the user presently resides in Los Angeles. We refer to such 2nd-order logic as “derived features” of ID Score.
Note on Selection of Vendors
Three main factors are considered for determining which vendors are most useful for ID Score:
- Decisioning Tools: Ensuring that we are aligned on how the vendor determines what data to pass on to use and how they make assessments about trustworthiness.
- Coverage: Ensuring that there are no gaps or redundancies in the data.
- Sources: Ensuring that certain groups are not underrepresented or overrepresented.
Enhanced Verification Measures
After receiving the augmented data from other identity verification vendors, Synapse uses machine learning models to compare against previously-seen data patterns in Synapse's ecosystem. Internal thresholds are in place to determine when requests for additional documentation from our users are necessary to help increase that the user is who they purport to be.
Sub-Resources
Updated over 4 years ago