Artificial intelligence for banking fraud prevention.
A presentation on how it takes its root in the digitalisation ways and how it impacts customer experience.
Artificial intelligence for banking fraud prevention
How it takes its root in the digitalisation ways
How it impacts customer experience
Legitimacy
Software Editor / Yverdon / 2 former students
Big Data Analytics - banking institutions - fraud prevention
Founded 2018 – long incubation – developing 2012
Figures
Sales Turnover
Only 8 years
A revolution in society / economy – 3rd industrial revolution
Iphone revolution our society
connection : we have a device connecting us to others and to services 24/7, but not only ( … Windows mobile)
User Experience : one click to reach key services and experiences
This interconnection has been key for many things:
Social network rise : symbiotic relation between smartphones and facebook ( )
Many other phenomenas
Consequence:
Millenials , GenXers : almost born with an iphone1) immediacy, 2) all about me myself and I (egocentricity / individualization) 3) Service : when I want, where I want, how I want
Change of Use / change of habits / change of behaviours => digitalization of society
difitalization of corporations and services (Uber, Netflix, Amazon, Paypal)
Yesterday – in 2008, we were amazed by the first smartphones.
Today they have almost become a part of ourselves. We cannot go without them anymore.
Nowadays, new technologies emerge first in the consummer market and then spread into business. New solutions emerge every month and corporations cannot keep up the pace.
This new reality has a name : it’s the consumerization.
.. Cray / iphone
-- 10’000 times more powerfull (1M computer moon)
People are used to be connected all the time, with highly efficient devices on highly responsive services, everywhere and for every possible need.
Today over 4 billion people are interconnected and exchange data, everywhere, all the time ,and for every possible need
Is it the biggest invention of the decade ? Likely, but the previous decade, not the current one.
The real revolution that is coming is the Internet of Things …
Tomorrow, in a few years, Gartner: over 40 billion objects will be interconnected, all the time, everywhere and for every possible need
Another story …
I cannot stress enough how much this is important and what it means in terms of change of society.
Today, we are inter-connected on different kind of medias, during a continuous time and for every possible need.This has become a part of the human behaviour.In a few years the majority of the workforce will be composed by millenials, by people almost born with an iphone.
In 2018, over 4 billion people are connected all the time, everywhere and for every kind of needs.
Again:
Change of Use / change of habits / change of behaviours => digitalization of society
digitalization of corporation and services
…
Mbank … (TODO recover from octo)
Challenges : change of use / change of behaviours / change of means force banking institiutions to adapt !
Overview of the challenges on 6 dimensions
Competitiveness
Think comparison web sites (comparis) / drop of everything not understood in 2 mins / all about me myself and I
Customer satisfaction
RDV amag / shopping 24/ 7 when I want, where I want and how I want
promise 0.5% mortgage interest / never applies / devastating impact …
Customer centricity
put customer back in the center of the preoccupations : meet him / inspire needs to him / listen to him
Marketing and branding
it’s all about reputation and innovation
consider the customer channels (mobile phones, youtube, social networks) and not the usual channels
Operational efficiency
Reduce costs, reduce delays, automated, digitalize
Risk management / mitigation
new channels : attack surface increase
more risks better risk mitigation techniques
audit / internal control : continuous, comprehensive, automated, real-time
fraud costs explodes
IMHO the most important challenges banks are facing with the digitalization and the changes of use and behaviours.
Happily, new technologies and these changes also offer opportunities
What are these opportunities on the same 6 dimensions
Competitiveness
Digital products are naturally simpler
Big Data analytics and AI enables to build
Customer satisfaction
A chatbot or an assistant app never sleeps, unlike a branch umployee
In an online world, positioning products and pricing is natural
Customer centricity
Getting online and digital with today technologies is not difficult
Technology give banks a chance to meet the customer and set themselves apart in the industry
Big Data analytics enables banks to understand customer needs and trends in an unprecedented way
Marketing and branding
Again, it’s all about innovation and reputation
The digital world offers unprecedented opportunities to convince a potential customer to buy a product : thin of try and buy, sandboxes, universality of channels
Operational efficiency
Technology is an enabled to process automation, dematerialization and digitalization
AI Analytics offer a brand new world of business and financial insights
Risk mitigation
Big Data Analytics and new UI technologies : dashboards, data visualization, real-time KPIs and KRIs
Artificial intelligence for fraud prevention
Real-time is never been so close
Conclusion : just as technology initiates change of behaviour and uses that challenges banking institutions, technology also offers unprecendented opportunities to catch up with these challenges
AI is the next step towards meeting these challenges and benefiting from the opportunities of the technology
- Show a set of initiatives in these regards
AI make banks smarter.
AI leads to better customer intelligence and thus a better customer experience—a key to increasing profit.
Examples:
AI learns the behaviors of market participants learn how markets behave enable better risk assessments
AI improve banks’ customer service in several ways – me and my banker (takes him huge time) – AI in no time and where, how, when I want
3 ways
Customer Experience revolution : when putting technology in direct contact with the customer (we’ll see examples)
AI analytics : improve operational efficiency in various domains (investment research, credit scoring) or provide personalized advisory to customers (we’ll see examples)
Risk mitigation : better fraud detection, as far as fraud prevention, more efficient AML controls, more efficient compliance controls, etc.
Let’s see some examples.
Note : worried 2 years ago when writing slides => banks caught up => AI has been key
Voice Assisted Banking
Physical presence is fading - technology empowers customers to use banking services -> voice commands and touch screens.
Natural language processing technology answer questions, find information, and connect users with various banking services educes human error, systemizing the efficiency.
Barclay : voice chatbot
VNLP : customers talk to a device and get information they need for vital transactions.
ML model the characteristics of the customer—for example, incomes and typical investments—and predict their preferred investment behavior and interests such as stock choices.
ML run in background, VNLP gives advices
RBS – chatbot luvo Luvo is a NLP AI bot which will answer customer's questions and perform simple banking tasks like money transfers. If Luvo is unable to find the answer it will pass a customer over to a member of staff.Not only advises but performs simple tasks.
BoA - Chatbot Erica
ML and predictive analytics to provide financial guidance. Erica can also help customers with simple transactions such as checking account status or simple payments.Also voice (NLP and VNLP)
Goive sparing and investment advices.
Challenged addressed by these initiatives
Opportunities actionned by these
Realtime Big Data processing with Machine Learning : provide personalised, value-added products to customers as it learns about spending habits or investment profiles.
Data-driven AI applications for financial decisions : advice, calculations, scoring and forecasts, for the bank or for the customers
RBS : automated lending process
approve commercial real estate loans up to $2.7 million—a process that normally takes days—in less than 45 minutes. The 2017 AI-driven launch is part of the bank’s broader digital and innovation agenda.
UBS "virtual research agents " that can perform investment research to near-human levels.imitate the quality of an investment analyst.
screen through market data, through SEC filings and do a company valuation with all of the inputs that a human analyst would use
UBS SmartWealth
ask customers a set of questions so that a machine-learning algorithm can assign them a risk category and invest their money in a specific and portfoliobring the fees attached to investing down to attract more customers into the bank smaller customers that would not be worth it for an asset manager chatbots … mimic what an asset manager provide to HNWI – private banking for retail customers
Fraud detection / AML - advanced significantly due to improvements in artificial intelligence.
Companies like MasterCard and Visa have been using AI to detect fraudulent transaction patterns for several years now.
react proactively and inform the customer.
Transaction analytics but also behaviour analysis (suspicious behaviour, not only transactions / ZugKB)
Lloyd …
HSBC has also been working with the London-based big data startup Quantexa to help the bank spot potential money laundering activity.HSBC has been piloting the technology since 2017, which uses AI techniques to analyse internal, publicly available, and transactional data within a customer’s wider network to spot rogue behaviour. It is now integrating Quantexa technology into its systems this year.
NetGuardians …
My conclusion on the intiatives I have been mentionning today
We have seen some examples if initiatives and the challenges they address as well as the opportunities they activates
AI is key to addressethe challenges of the digitalisation
AI is the state of the art, the bleeding edge of the opportunities coming from the digitalizatiin
AI enables to go faster, further, stronger in the digital transformation
Would want to speak present more in details what we do at NetGuardians et and how it impacts customer experience
In February 2016, a group that we deem around 20 persons, composed by financial experts, software engineers and hackers have attacked the information system of the Bangladesh Central Bank.
They manage to compromise the bank internal gateway to the SWIFT Network. The SWIFT network is the international banking messaging network used by banks to communicate and transfer money through electronic wire.
The pirates used the SWIFT network to withdraw money from the Bangladesh Central bank VOSTRO account by the US Federal Reserve.
They manage to transfer 81 millions USD to the Philippines and used the Philippino casinos to launder the stolen funds.
As a sidenote, the fact that they have stolen “only” 81 million USD is an amazing luck for the bank, or rather an amazing bad luck for the cybercriminals.
An Anti-Money laundering system – rule-based - deployed in the US federal Reserve blocked the 6th transaction because the beneficiary name contained the word “Jupiter”. Jupiter was on a sanction screening list in the US because a cargo ship navigating under Iranian flag is called “Jupiter” something. The 6th transaction being blocked, all the further ones, around thirty, have been blocked as well.
But 5 transactions pass through before the 6th has been blocked by the Fed and went further through the correspondent banking network
Another transaction has been blocked by the Deutsche Bank, a routing bank, because of a typo “ Shilka Fandation” instead of “Shilka Fundation”
So only 4 transactions our of 35 successfully arrived to the Philippines and as such the total loss have been reduces from 951 million USD initially intended to “only” 81 millions USD
The Retefe worm is a worm developed by a team of cybercriminals targeting specifically the ebanking platforms of small and mid size Austrian And Swiss Banking Institutions
The worm is used by the thieves to take control of the victim’s ebanking sessions and to submit fraudulent transactions to the system
This worm is 4 years old
For 4 years, fraudsters keep on updating it, modifying it and extending it to counter the anti-viruses software and the specific protections put in place by the banks.
This worm is 4 years old and nevertheless, as pointed out by the Computer security section of the federal finance department, it is still making today between 10 and 90 victims in Switzerland and Austria,
Today, in the swiss banks …
My conclusion from these examples is as follows:
Today, fraudsters and cybercriminals are professionals
The time when fraud was coming from a little hacker working in his garage or a back-office employee disappointed by his bonus, is over.
Today, attackers are professionals who have industrialized their methods
In the second half of the 2000’s, however, the costs linked to fraud, increasingly external, the complexity of attacks and the maturity of attackers rise.
Banking institutions react by deploying quite massively and for the first time specific analytics systems aimed at detecting banking fraud, both external and internal.
At this time, these systems are rules-engines that work by checking or searching pre-defined and well defined conditions within the data extracted from the information system.
In a way these systems can be considered as simple extensions of the security checks and rules implementing directly within the operational information system.
The solutions come most of the time from the AML – Anti Money Laundering – World, their editors having understood that banking fraud was a way to extend their sales
A very simple rule example is show at the bottom of this slide.
At this time, a first set of papers have already been published on the success, still somewhat relative in this early days, of some Machine Learning approaches implemented towards banking fraud detection.
But Machine Learning and Artificial Intelligence are considered with a lot of condescension and skepticism.
Bankers and their engineers are not willing to consider an approach whose interpretation of results is deemed fuzzy.
NetGuardians has been built at these times and the NetGuardians platform could be seen as a gigantic rule engine,.
Unfortunately, the reality of fraud and financial cybercrime evolved fast and dramatically.
Let me give you two examples
Artificial Intelligence provides the solution to this problem
In 2016, we started at NetGuardians to integrate the first advanced algorithms, so called Machine Learning algorithms, in our systems.
We let an Artificial Intelligence analyze continuously the history of billions of transactions in the system and learn about individuals habits and behaviours.
With big data technologies, AI can analyze a very extended depth of history and build dynamic profiles for each and every individual related to a financial transactions.
Individuals are both Customer and Users (Internal Employees)
Profiling customers is required for both Internal and External Fraud.
Profiling users is required for Internal Fraud.
Big Data technologies are key to maintain these profiles up-to-date in real time by tracking each and every interaction between the user and the bank systems
In addition to a financial transaction direct characteristics such as the beneficiary, the target bank country, the amount of the transaction, its currency, etc., the machine can correlate a lot of indirect characteristics, such as where in the world was located the ATM where the user withdrawn money from, where was he connected to his ebanking session, etc.
For each and every individual a dynamic and up to date profile captures his behaviour and his habits
Then, each and every financial transaction, regardless of its type, it being a security trade order, an ATM withdrawal or an ebanking payment, is compared against the user profile and a risk score is computed.
Based on this risk score, the machine eventually decides whether the transactions is genuine or not and whether it requires further investigation by a human analyst within the bank.
The machine can look at the big picture and analyze transactions at a broader scale.
Recall the Audi example. When such a transaction is very unusual for a specific customer, looking at other customers with similar conditions, habits and behaviour is required.
And here again AI comes in help.
AI can analyze behaviours and habits of customers and group together the people with same patterns. People that are the same age, same wealth level, same origins or same … will have a strong tendency to behave the same: for instance drive the same kind of car, such as an Audi, live in a flats of the same size, pay the same amount of telephone bills at the end of the month, etc.
The machine can analyze customer activities and transactions on the large scale and cluster together customers with same behaviour.
Then, these groups can be profiled just as individuals.
And finally, a transaction can be scored against the customer group profile in addition to the customer profile.
Recalling the Audi example. When scoring this specific payment against the individual profile, the transaction will be flagged as suspicious.
Scoring it against the group profile will clearly indicate that it’s a genuine transaction. People buy new Audis every day, especially in Switzerland
[On blank page]
Let me give you a simple example of what I mean by analyzing a customer’s interaction with the banking Information system.
The interactions of a customer with the ebanking application is the simplest example I can come up with.
[Page down on Genuine User]
Imagine the situation of a genuine user of the ebanking platform whose behaviour when inputting is payments is always the same
He logs in the ebanking platform
He looks at his account balance
He performed all his payment, from input to validation, many of them
He checks his pending orders, making sure he missed none of them
He logs out the platform
[Page Down on Worm]
Now if a worm hijacks the ebanking session, the worm will do none of that
The worm will likely go directly from login to payment input, validation to logout
Here I am only showing transitions but one can also consider User think time, keyboard stroke speed, etc.
[Page Down on principle]
AI can analyze all this behaviour and activity tails a user or customer leaves on the banking information systems and build a model capturing this behaviour
Then, when an individual action is performed, the machine can compute the likelihood of that action to be performed by a legitimate user or an attacker based on the past activity.
And here as well, AI can build profiles of this activities and their likelihood both at individual level and group level through clustering techniques.
…
NetGuardians digitalizes and improves Fraud detection
Sysmosoft digitalizes the call-back
A breakthrough : not only we reduce the amount of hits, i.e. the amount of confirmations asked to customers, but we automate the handling of these reconfirmations and customer call-back.
For the customer: a reconfirmation call-back is received a few minutes after the transaction is input
- confidence / reputation /
- ease of re-confirmation – one fingerprint (strong authentication)
…
In the future, the callback will increasingly be handled by chatbots and robots
Just answer a few questions
Validate or reject the transaction
CONCLUSION
NetGuardians makes fraud prevention enter the digital era :
+ fully digitalized and automated process / No more human intervention
+ AI / Big Data
- Customer experience impacts
+ Seamless user experience for reconfirmation
+ indirect but essential : protecting the customer assets
+ protecting the banking institution reputation and brand
- I would like to conclude my presentation on the netx slide
Banks are embracing AI / more and more initiatives / finally catching up with fintechs (acquisition …)
Implement AI to replicate user experience seen in eCommerce and uber, netflix, etc.
Amazons and Uber aren’t suffering from regulatory pressure …
Regardles s– innovative spirit and digital mindset first class user experience within a regulated environment
3 ways to leverage power of AI
Millenials and GenXers willing to share personnal information in exchnage for a more customized, streamlined service (unlike baby boomers)All “about me myself and I”, “where I want, when I want, how I want” meet the customer (channels) / personalized service / recommendations (don’t‘ like searching)
Few banks have the resource of BoA or UBSFirst dig into cost-saving applications (Operational efficiency [automate, digitalize internal processes], risk mitigation [NG]). Then use these savings to invest on more interesting applications (CX / UX)
Wells-fagro : Ai Enterprise Solution Team ! – connect bank staff with AI experts / brainstorm on applications !
Last worls : a few years ago I was convinced that this schema would be the truth in the coming 10 years…Today I am less pessimistic – many initiatives in bank in regards to digitalization and CX – THANKS TO AI !!!