Intelligence helps banks and institutions detect anti
money-laundering by providing enterprise-wide transactional
analysis that analyse multiple situations, detect unusual
patterns in the data and flag-off suspicious transactions,
says Dr Kaustubh Chokshi, CEO of Intelligent Business
is well known that black money has been the bane of governments
in the developing world, depriving them of much-needed
tax revenues and crippling their already-burdened economies.
But the impact of black money and its laundered equivalent
is far more onerous than mere tax evasion in developing
countries, and its tentacles extend globally into the
illegal arms trade, drug trafficking and the funding of
wonder then that the international community is putting
in place stringent regulations to combat money laundering,
and pressurising the banking industry to comply with the
implementation of these regulations.
general, money laundering follows a three-stage process.
First comes placement, whern black money is injected
into the financial system. Then comes layering,
when money is layered or spread across multiple entities,
in order to conceal the identity of the source. The last
stage is integration, which is routing the money
back to the original entity through legal channels.
a leading management consulting firm, has estimated that
funds worth anywhere from $590 billion up to a staggering
$1.5 trillion are laundered annually through the global
economy, amounting to 2-5 per cent of global GDP. Closer
home, estimates on the amount of black money in the Indian
economy vary from 20 per cent to 40 per cent of India''s
Me If You Can
As money-laundering operations can have a crippling effect
on the economy, the Reserve Bank of India (RBI) has devised
a series of banking practices that can check the proliferation
of this menace in the country. The "know your customer"
(KYC) guidelines require that banks obtain authenticated
identification from prospective clients at the time of
opening of new accounts.
there is the Prevention of Money Laundering Act, 2002
(PMLA 2002), which mandates that in addition to client
identity verification, banks and financial institutions
need to maintain and furnish records to the various regulatory
authorities as defined by the Indian government. It also
allows regulatory authorities to freeze, seize and confiscate
suspect accounts. Besides these two important laws, there
are other laws and guidelines formulated by the government
or regulatory bodies such as the Securities and Exchange
Board of India (SEBI).
course, history has shown us time and again that whenever
laws are created, criminals find loopholes to work around
them. In an effort to detect money-laundering activities,
many Indian banks have deployed anti money-laundering
(AML) software solutions. However, as many of these solutions
follow fixed rule-based methodologies for detecting anomalies,
any novel laundering technique easily slips through the
net. For instance, a typical AML software solution that
flags or sends out alerts in case a transaction is above
a specified threshold will be ineffective if the said
amount is split up and/or spread across multiple accounts.
take the example of an organisation that reports exceptional
profits quarter after quarter, even as all other outfits
in the same industry segment are faring poorly. While
the profitable company might be truly outstanding, there
is also a high probability that the numbers are being
manipulated and the outfit is serving as a dummy front
for some other companies or underhand activities.
the company''s account is examined on a standalone basis,
no suspicions would be raised. However, cross-industry
analysis would set the alarm bells ringing. Traditional
AML solutions are usually incapable of detecting such
anomalies, as they do not take a holistic view, and can
only work on fixed, logic-based rules.
To counter money-laundering operations, banks and financial
institutions need solutions that take an enterprise-wide
view of transactional analysis. These solutions must have
the ability to analyse multiple situations, detect unusual
patterns in the data and flag off suspicious transactions
when things seem amiss.
recent times, solutions powered by artificial intelligence
(AI) technologies have emerged as a powerful and effective
option for rising above the shortcomings of traditional
AML solutions. AI-based AML solutions are far more effective,
as they use techniques like Bayesian inferencing and neural
networks, which learn by example and experience in a non-linear
mode (similar to how the human brain works), rather than
merely being programmed to rigidly perform specific tasks.
discussed in earlier articles of this series, a neural
network is initially "trained" or primed with
large amounts of historical data and rules about the data
relationships. Once trained, a neural network becomes
an "expert" in its specific area of operation.
It can then offer projections and trends, and sniff out
suspicious transactions in current data that could be
fraudulent in some way or the other, for human experts
to act upon.
inferencing enables calculation of the probability of
a new event on the basis of earlier probability estimates
of events in the past, derived from existing empiric data.
With the Bayesian approach, one can use objective data
or subjective opinion to specify a response. Once this
is done, the earlier probabilities can then be used to
make better decisions.
AI-powered AML solutions thus derive meaning from complex
or imprecise data, recognise patterns, and determine trends
that most human beings or other computer techniques fail
to identify. In addition, they become increasingly intelligent
as more and more data enters the system, thus rendering
them far more effective than conventional AML solutions
in the long run.
AI-Powered anti-money laundering
An effective AML solution must have the ability to draw
inputs from a variety of sources, and provide a single
view of the customer and the financial relationships he/she
has with multiple entities. AML solutions must provide
functions such as "watch list" name screening,
business relationships and country-related information.
AML solutions must also give banks the ability to identify
situations where there is a sudden spurt of activity in
specific accounts, or there are a lot of internal transfers
happening between accounts. As money-laundering techniques
change constantly, banks must have the ability to predict
future scenarios and react appropriately.
adopting an AI-based approach, organisations can build
statistical models that, over a period of time, can be
used to predict the money-laundering risk posed by different
transactions. They can also be very effective in developing
alternative scenarios and modelling the profile