Risk assessment and monitoring has become more
challenging with the rapid growth in size and complexity of the
interconnected global financial markets. China, India and the
rest of Asia have hundreds of millions of consumers joining
the middle class every year and much of this population has
limited financial transaction history and are not tracked by any
credit bureaus. In the United States, 26 Million consumers are
not tracked by FICO and related credit bureaus and that
number has grown to 15% of the entire population as of 2018.
This presents a unique challenge for credit risk assessment
and monitoring. The regulatory landscape gets more
complex each year with the fines for the United States Office
of Foreign Assets and Control (OFAC) sanctions ranging from
$12,500 to over $8.9 Billion for each sanctioned bank. The
regulatory risk assessment and monitoring rises in
importance as a result. The proliferation of complex financial
instruments, such as credit default swaps and mortgage-
backed securities have increased the complexity of liquidity
risk assessment and monitoring and the cost of getting it
wrong is in Trillions - The great recession of 2008 due to the
mismanaged liquidity risk around subprime mortgages
resulted in a staggering loss of 2 Trillion USD to the global
growth and threatened the stability of global markets.
Traditional Solutions Are Missing the Mark
Virtually all existing risk assessment and monitoring systems are
built upon relational databases, which store information such as
counterparty, account, transaction, stakeholders, financial
instruments and derivatives in separate tables, one for each type of
business entity. The relational databases are great tools for
indexing and searching for data, as well as for supporting
transactions and performing basic statistical analysis; however, the
relational databases are poorly-equipped to connect across the
tables or business entities and identify hidden relationships and
risks from those relationships going across as many as 10 or more
layers of transactions, accounts, and persons.
Using the relational
databases, in order to find potential connections, analysts need to
join a number of large tables to run the queries. Such queries could
take hours or even days to run, rendering any meaningful analysis of
linkages among parties and transactions practically impossible.
Assessing and monitoring risk also requires going beyond the
internal data for the individual account or person and connect
it up with the information from third party sources such as
OpenCorporates and the World-Check database from
Thomson Reuters containing information on Political Exposed
Persons (PEP) and the government-sanctioned entities. In
case of credit risk assessment, this means integrating non-
traditional data sources such as mobile wallet and
eCommerce transactions as well as microloan repayments.
The relational databases with their rigid schema are not well
suited for marrying the internal data with multiple external
data sources with ease.
Why TigerGraph - a Native Parallel Graph Database for Risk Assessment and Monitoring?
Credit Risk Assessment and Monitoring
As much as 15% of the US population isn’t tracked by FICO and
associated credit bureaus. Fintech startup IceKredit is creating credit
scores for these “credit invisible”, the subprime population in the
United States as well as in China and Southeast Asia by tapping into
alternate sources of credit history. Consider the example of
IceKredit where a 360-degree view of the credit risk computed
using TigerGraph leveraging any financial history using traditional
data sources and combining it with the new data sources such as
transactions on eCommerce sites such as WeChat and JD.com for
China, mobile wallet records such as Alipay, Venmo and Paypal
and the loan repayment records for Micro-loan and Peer-to-peer
lending service providers such as CashBUS and Crowdo in Asia.
With access to accurate third-party data (from the
government, public and private sources), IceKredit uses
Machine Learning and AI for custom advanced models and
analytics used to build comprehensive credit views for
applicants. IceKredit’s anti-fraud engines further quantify
an applicant’s fraud probability and compare it with actual
business activity, helping clients prioritize leads and make
smarter decisions on acquiring customers based on risk.
Graph analytics is key to IceKredit’s success in identifying undisclosed relationships and connections within data, and
to assigning and updating risk ratings in real time. Graph
analytics is also being used by IceKredit to assist and
improve efficiency for the investigations around potential
financial crimes violations.
Consider the example, where a bank receives an
application for a new corporate account for a company
ABC. During the customer due diligence or CDD
process, the company fills out information including
their street address as well as three officers for the
company - Jim Smith, Wei Zhang and Maria Garcia.
TigerGraph connects the company ABC officer Wei
Zhang as a signatory for another company XYZ which
has a local politician listed as a significant stakeholder
From this information, TigerGraph connects
the local politician with a third party database containing politically exposed persons (PEP) and also
finds that one of the street addresses listed for the
politician is same as the address listed for the new
company ABC on their account application. All of this
raises the risk associated with company ABC, raising
an immediate CDD alert to be looked at and
investigated further by the banking staff.