Collating varied types of data in different formats and making sense of them by applying machine-learning will enable businesses to counter security threats
The payments and ecommerce landscape has undergone significant changes in recent years. At a local level, commerce and banking moved to a digital-first, standard format. At a global level, and specifically in developing markets, there has been a huge transition from “mum and dad” shops straight to online commerce. People no longer need banks or shops; they need banking and commerce services.
However, as much as this offers new and exciting online opportunities to business, unscrupulous individuals are also taking advantage of easy-to-access fraud tools, exploiting vulnerabilities and targeting weaknesses in the security infrastructure of unsuspecting organisations.
Rahul Pangam, co-founder and chief executive of fraud prevention technology firm Simility, acquired by PayPal earlier this year, believes that companies are now operating in an environment where they have to assume, even with the most sophisticated security solutions, there are no cast-iron guarantees in a “post-breach normal” world.
“How to manage risk in this environment is different than how to manage it in a world where data can’t be compromised. As transactions happen, risks need to be managed in real time,” says Mr Pangam.
The most pressing challenge for companies is to balance customer experience effectively with security and regulatory issues. Customers have become accustomed to frictionless digital experiences and want payments to be made immediately, at the same time as cybercriminals are utilising increasingly sophisticated techniques. An increasingly complex regulatory environment that necessitates businesses comply with PSD2 (Second Payment Services Directive), faster payments and open banking adds a further burden to firms.
“It’s not realistic to treat every user as a fraudster, as they will dislike the experience and go to a competitor, but equally trusting each login attempt will let fraudsters in at some point,” says Mr Pangam. “Achieving the best of both worlds by offering a positive user experience and implementing appropriate fraud prevention solutions can be achieved by analysing each user and their activity in a nuanced way.”
Fraud management is no longer a linear decision, with multiple factors needing to be considered and weighted in real time, which is something traditional tools are unable to accomplish. By focusing on a single instance of fraud or cybercrime, the wider context is ignored. For example, fraudsters may move money from a savings account to a current account and leave the money untouched. The bank may find this suspicious, but they might not act on it, then a fraudster may use a stolen ATM card to cash out the account.
“Two distinct events may not seem related on the surface, but by using platforms such as Simility to harness disparate data, actionable insights can be uncovered to identify anomalies,” says Mr Pangam.
Data is the driving force behind effective fraud management and businesses that are able to turn data into a strategic advantage will have an edge over competitors. Simility’s Adaptive Decisioning Platform was built with a data-first approach in mind and offers a complete view of customer behaviour and activity, which ensures every piece of information can be utilised and all regulatory requirements are met.
The multi-channel aspect of fraud is increasing as fraudsters are becoming even more adept at circumventing security tools. Pulling together varied types of data in different formats and making sense of them by applying concepts of machine-learning will enable businesses to adapt effectively to future security challenges.
With Simility, businesses not only have the processing power to analyse huge datasets, but they also gain the ability to customise user interactions. “If you see access from a new location or device, while it could be the user travelling, it could also be a fraudster. Why ask all users the same verification questions? Personalise services based on risk factors, such as location, device and behaviour, to make the process more seamless,” Mr Pangam concludes.
For more information please visit simility.com