How AI mitigates Fraud in BFSI segments
3AI May 13, 2017
The Banking and Finance sector (BFSI) is witnessing one of its most interesting and enriching phases. Apart from the evident shift from traditional methods of banking and payments, technology has started playing a vital role in defining this change.
Mobile apps, plastic money, e-wallets and bots have aided the phenomenal swing from offline payments to online payments over the last two decades. Now, the use of Artificial Intelligence (AI) in BFSI is expediting the evolution of this industry.
But as the proliferation of digital continues, the number of ways one can commit fraud has also increased. Issuers, merchants, and acquirers of credit, debit, and prepaid general purpose and private label payment cards worldwide experienced gross fraud losses of US$11.27 billion in 2012, up 14.6% over the previous year1. Fraud losses on all general purpose and private label, signature and PIN payment cards reached US$5.33 billion in United States in the same period, up 14.5%1. These are truly big numbers, and present the single-biggest challenge to the trust reposed in banks by customers. Besides the risk of losing customers, direct financial impact for banks is also a significant factor.
Upon reporting of a fraudulent transaction by a customer, the bank is liable for the transaction cost, it has to refund merchant chargeback fee, as well as additional fee. Fraud also invites fines from regulatory authorities. The recently-passed Durbin Amendment caps processing fee that can be charged per transaction, and this increases the damage caused by unexpected fraud losses. The rapidly rising use of electronic payment modes has also increased the need for effective, efficient, and real-time methods to detect, deter, and prevent fraud.
Nuances of Banking Fraud Prevention Using AI
AI enables a computer to behave and take decisions like a human being. Coined in 1956 by John McCarthy at MIT, the term AI was little known to the layman and merely a subject of interest to academicians, researchers and technologists. However, over the past few years, it is more commonly seen in our everyday lives; in our smartphones, shopping experiences, hospitals, travel, etc.
Machine Learning, Deep Learning, NLP Platforms, Predictive APIs and Image and Speech Recognition are some core AI technologies used in BFSI today. Machine Learning recognises data patterns and highlights deviations in data observed. Data is analysed and then compared with existing data to look for patterns. This can help in fraud detection, prediction of spending patterns and subsequently, the development of new products.
Key Stroke Dynamics
Key Stroke Dynamics can be used for analysing transactions made by customers. They capture strokes when the key is pressed (dwell time) and released on a keyboard, along with vibration information.
As second factor authentication is mandatory for electronic payments, this can help detect fraud, especially if the user’s credentials are compromised. Deep Learning is a new area in Machine Learning research and consists of multiple linear and non-linear transformations. It is based on learning and improving representations of data. A common application of this can be found in the crypto-currency, Bitcoin.
Adaptive Learning is another form of AI currently used by banks for fraud detection and mitigation. A model is created using existing rules or data in the bank’s system. Incremental learning algorithms are then used to update the models based on changes observed in the data patterns.
AI instances in Insurance for Fraud Prevention
Applying for Insurance
When a customer submits their application for insurance, there is an expectation that the potential policyholder provides honest and truthful information. However, some applicants choose to falsify information to manipulate the quote they receive.
To prevent this, insurers could use AI to analyse an applicant’s social media profiles and activity for confirmation that the information provided is not fraudulent. For example, in life insurance policies, social media pictures and posts may confirm whether an applicant is a smoker, is highly active, drinks a lot or is prone to taking risks. Similarly, social media may be able to indicate whether “fronting” (high-risk driver added as a named driver to a policy when they are in fact the main driver) is present in car insurance applications. This could be achieved by analysing posts to see if the named driver indicates that the car is solely used by them, or by assessing whether the various drivers on the policy live in a situation that would permit the declared sharing of the car.
Claims Management & Fraud Prevention
Insurance carriers can greatly benefit from the recent advances in artificial intelligence and machine learning. A lot of approaches have proven to be successful in solving problems of claims management and fraud detection. Claims management can be augmented using machine learning techniques in different stages of the claim handling process. By leveraging AI and handling massive amounts of data in a short time, insurers can automate much of the handling process, and for example fast-track certain claims, to reduce the overall processing time and in turn the handling costs while enhancing customer experience.
The algorithms can also reliably identify patterns in the data and thus help to recognize fraudulent claims in the process. With their self-learning abilities, AI systems can then adapt to new unseen cases and further improve the detection over time. Furthermore, machine learning models can automatically assess the severity of damages and predict the repair costs from historical data, sensors, and images.
Two companies tackling the management of claims are Shift Technology who offer a solution for claims management and fraud detection and RightIndem with the vision to eliminate friction on claims. Motionscloud offer a mobile solution for the claims handling process, including evidence collection and storage in various data formats, customer interaction and automatic cost estimation. ControlExpert handle claims for the auto insurance, with AI replacing specialized experts in the long-run. Cognotekt optimize business processes using artificial intelligence. Therefore the current business processes are analyzed to find the automation potentials. Applications include claims management, where processes are automated to speed up the circle time and for detecting patterns that would be otherwise invisible to the human eye, underwriting, and fraud detection, among others. AI techniques are potential game changers in the area of fraud. Fraudulent cases may be detected easier, sooner, more reliable and even in cases invisible to the human eye.
Those who wish to defraud insurance companies currently do so by finding ways to “beat” the system. For some uses of AI, fraudsters can simply modify their techniques to “beat” the AI system. In these circumstances, whilst AI creates an extra barrier to prevent and deter fraud, it does not eradicate the ability to commit insurance fraud. However, with other uses of AI, the software is able to create larger blockades through its use of “big data”. It can therefore provide more preventative assistance. As AI continues to develop, this assistance will become of greater use to the insurance industry in their fight against fraud.