Published: 9th September 2018
Fraud has been a major issue for all banks and financial institutions every since they first opened their doors. As the technical power has increased and improved the customer offerings from the banks, so to has the opportunity for fraud. Now it is possible for fraud to be committed from different unrelated countries within minutes.
The international connection between banks is performed by the Society for Worldwide Interbank Financial Telecommunication (SWIFT). During 2015 and 2016, a series of cyber-attacks using SWIFT were reported, resulting in the successful theft of millions of dollars. The attacks exploited vulnerabilities in the systems of member banks, allowing the attackers to gain control of the banks' legitimate SWIFT credentials. The thieves then used those credentials to initiate SWIFT funds transfer requests to other banks, which, trusting the messages to be legitimate, then sent the funds to accounts controlled by the attackers. The attacks were planned to happen on public holidays during different global regions, giving the attackers an extra 24 hours to move the funds before any traces and reversals could occur. In one attack, the attackers withdrew $101 million USD from a Bangladesh Bank account at the Federal Reserve Bank of New York. $20 million was sent to Sri Lanka, but the hackers misspelled "Foundation" in their request to transfer the funds, spelling the word as "Fundation". This alerted Deutsche Bank, who put a hold on the payment. $81 million was sent to the Philippines. This payment occurred during the Chinese New Year. The Bangladesh Bank, through SWIFT informed the local bank in the Philippines to stop the payment, refund the funds, and to "freeze and put the funds on hold”. Chinese New Year is a bank holiday in the Philippines and a SWIFT message from Bangladesh Bank was received a day later. By this time, a withdrawal amounting to about $58.15 million had already been processed by the local branch.
And that is just one example of the billions of dollars being lost to fraud every year. Fortunately, artificial intelligence has great potential to reduce fraud. As automated fraud detection tools get smarter and machine learning becomes more powerful, the amount of fraud could actually decrease.
And now with the addition of real-time payments in Australia (using the NPP), minimised fraud in real-time is more important than ever.
One definition by Technopedia states that “Artificial intelligence (AI) is an area of computer science that emphasizes the creation of intelligent machines that work and react like humans. Machines can act and react like humans only if they have abundant information relating to the world. Artificial intelligence must have access to objects, categories, properties and relations between all of them to implement knowledge engineering. Initiating common sense, reasoning and problem-solving power in machines is a difficult and tedious task.” (https://www.techopedia.com/definition/190/artificial-intelligence-ai)
In a recent report by security company McAfe, it is estimated that cybercrime currently costs the global economy some $600 billion, or 0.8% of global gross domestic product. One of the most prevalent forms and preventable types of cybercrime is credit card fraud, which is exacerbated by the growth in online transacting. The speed at which financial losses can occur when credit card fraud takes place makes intelligent fraud detection techniques increasingly important.
Because of the availability of large volumes of customer data, together with transactional data that is updated as transactions occur, AI can be used to effectively identify credit card and direct transfer behaviour patterns that are irregular for specific customers. When, as the life circumstances and spending habits of a customer changes, the model would automatically adjust what it views as potentially fraudulent transactions. This could reduce actual fraudulent transactions and minimize false fraud flags (false positives).
For example, if you decide to book an overseas holiday, most traditional fraud detection systems would issue a red-flag. This is due to your different buying patterns than previously stored. However, a smarter system would understand the patterns of human behaviour, and see that the purchase of an overseas holiday would then allocate that account to a different set of customer purchasing habits. It would then test your behaviour against transactions typical to that of the new cluster of users, holiday travellers, before automatically raising a fraud flag on your account. This would increase customer satisfaction by limiting the number of times that a customer can’t complete a transaction due an incorrect flagging and reduce the operational overheads of the financial institution, by preventing unnecessary interactions with such customers.
A new challenge for global fraud detection is the ability of cybercriminals to utilize unregulated cryptocurrency exchanges to cash out the return of their criminal online activities. While many exchanges follow some type or Know Your Customer (KYC) processes, it becomes clear that it is imperative to use the most advanced techniques available to fight cybercrime.
With AI’s ability to analyse data in real time, fraud teams are better equipped to predict fraud before it occurs and therefore minimise losses. AI reduces some of the noise of large amounts of data to focus on the real threats. With the introduction of the NPP in Australia recently, we can expect to see digital transaction processing converge with analytics providing better insights. Machine learning will enable organisations to look at more data, from more sources, and make better predictions with less uncertainty. However, automated bots could be working on both sides – and the next generation of AI-enabled fraud systems will also need to be prepared to tackle new and increasingly sophisticated fraud attempts and scams.
An emerging algorithm is based on the way people think. These are known as Convolutional Neural Networks and are based on the visual cortex, which is a small segment of cells that are sensitive to specific regions of the visual field in the human body. This new development in AI makes algorithms that were already intelligent infinitely smarter. This technology can study the spending data of an individual and be able to determine, based on this information, whether they performed the most recent transaction on their credit card or if someone else was using their credit card data. Implementing this type of solution to curb cybercrime, for example, will reduce the economic losses drastically.
Fraud has been taking place throughout history and has become more complex and difficult to stop as technology has improved. We are now in a position where we are also able to leverage technology to identify these fraudulent activities and stop them before they cause harm. Achieving this will reduce banks and financial institutions’ overall costs and improve customer satisfaction, and they will likely be more loyal to an institution that better protects their money. Ultimately, AI looks likely to be a disruption technology for the entire banking industry, leading not only to reduced cybercrime but happier clients and greater customer advocacy from them. Everyone wins.