Artificial Intelligence modern approach

Artificial Intelligence: A Modern Approach to Combat Fraud

Preventing fraud has never been an easy task… perhaps Artificial Intelligence (AI) is a modern approach to overcoming this age old problem. Not just for organisations but for individuals the possibilities are pretty incredible.

We’ve all heard about AI and the wonders that the likes of Google and Tesla are creating with it.

In the last few years we have barely been able to check out the latest news online without seeing something about one of the big corporates and AI, most recently Googles aborted attempt at an AI ethics council was catching the headlines.

Yet for all the leaps we have made, it wasn’t until just a few years ago self-driving cars were something learner drivers and science fiction fans could only dream of!

Now, Tesla has successfully put their first models on the market, even if they are a bit on the expensive side. And the next generation of truly autonomous vehicles is approaching rapidly.

At work, is making appointments and bookings getting in the way of your busy life? Google Duplex will make them for you over the phone just like a normal human, this was showcased in 2018 to the absolute amazement of the world.

In the home the likes of Amazons Alexa is able to deliver more and more benefit and information than we have ever been able to ask for, literally, before.

And of course, we can’t forget Siri, Apple’s loveable (well most of the time) helping hand who can set reminders and send texts when you aren’t able to yourself, in her latest patch she was even given the ability to open and launch applications with just a command!

But AI isn’t just about making our lives easier, at least not exclusively.

The media loves to focus on the amazing ways in which these multi-billion dollar companies are revolutionising the way we live our lives. What goes on in the background, however, is arguably more important but is harder to understand, and not quite so awe inspiring to talk about.

In areas such as financial services and big business, fraud prevention and detection has always been a struggle. With continued, rapid, advancements in the way in which transactions take place, it hasn’t been getting any easier.

Although we should really remind everyone, this applies as much to us as individuals as it does to big business.

With the rise in contactless payments, computerised assistants in stores and takeaways and online shopping, the way we spend our money has fundamentally changed, as have the risks to each of us from fraudsters.

Security giant McAfee launched an investigation in 2016 which found that cyber-crime, much of which is fraud, was costing the world around 0.8% of global GDP.

However, the future is not bleak as thanks to AI this is changing.

Financial institutions and many businesses now use software that tracks all transactions, from credit card payments to invoices, and detect when fraudulent behaviour takes place.

Better yet, the very best of these solutions can even highlight documents that are high risk based on intelligent business rules and some pretty incredible AI that can highlight when characters have been replicated across the same document.

They do this by using two branches of AI, machine learning and deep learning, which involve robots learning by example, allowing them to recognise abnormalities in spending patterns or a transaction process, and then reporting this before anything further can happen to the money.

In the past, forged invoices or stolen card details would often be overlooked until the damage was too much to undo. Or were only spotted post the event of payment meaning that recovery audit was the best way of attempting to regain some of this miss spent income.

From a personal risk perspective, the best-case scenario was that someone would notice a fraudulent payment when they received their statement. Of course, this often meant that they may only be able to cancel their card, preventing future usage but not reimbursing them for their money lost.

Now, however, we have AI, a modern approach to stopping fraud that detects the criminal activity almost instantaneously, meaning the money remains safely in the right hands. For many of us we will have received notifications from our banks or credit cards whenever an unusual spend happens.

Wouldn’t it be better if fraud was prevented all together?

Yes, of course it would.

As technology to help stop fraudsters advances, so too does the technology to aid them, so in reality fraud detection may be our best weapon at the moment. As with any form of criminal activity, those committing the crime are invested in ensuring that they are able to work around changes made.

Financial Fraud Action UK’s Fraud the Facts 2017 found that by using AI to detect fraud, only 64% was prevented.

Although this is a substantial amount of money saved, that still leaves £3.60 of every £10 unaccounted for.

Really this question is a nonstarter. It goes without saying that stopping fraud would be our best bet, and AI can help cut out large amounts.

Without fundamentally changing human nature and behaviour though reaching 0% fraud is unlikely to happen soon.

What does this mean for the future?

The company, Rainbird, has predicted that, if all UK businesses used AI to detect fraud, collectively they could save £7bn in five years.

They have also said that as new AI technology is constantly being developed, the 64% of money saved could easily become 80%. This becomes especially viable when we consider connectivity of these systems and the fact that they can pool their knowledge to improve protection.

The hope is that as more and more fraud is detected, the criminals behind it will become less incentivised to attempt to carry out the crime, as the risk of failure is too high. And this is a far easier way to approach it than trying to change their minds about good and bad…

AI is advancing every day, so more fraud is being detected than ever before, and this will continue to improve, meaning more fraud will be stopped and hopefully less will take place in the first place.

For organisations, the ability to avoid making fraudulent payments, and the subsequent costs of recovery auditing, is a real driver. This will make a massive impression on a company’s bottom line.

So yes, artificial intelligence is a modern approach to the old fraud problem.

Recommended Reading:



Post by John Stovold,
Marketing Manager ITESOFT

John Stovold has worked at ITESOFT since 2012. Driven by a desire to learn and educate John has used this to set himself up as a true thought leader in digital transformation of Accounts Payable and Finance. John really isn't that keen on writing in the 3rd person... But will when he has to.

Other articles