Recently, Couchbase and Revolut were jointly honored with the Anti-fraud Solution of the Year accolade at the prestigious FStech Awards. This was awarded in recognition of Revolut’s world-class fraud prevention system, Sherlock, and Couchbases’s enterprise-class NoSQL database with which Sherlock was built. As much as we were looking forward to donning our finest attire, alas the gala dinner was cancelled and replaced with a virtual experience in accordance with the current circumstances.
This recognition is meaningful for a number of reasons, one of which is celebrating the amazing work done by our customer Revolut, who built the app in only 9 months! But the award also brings to light the role that NoSQL is now playing in powering world-class financial services applications and solutions.
Read on to learn about Revolut’s award-winning solution and why it chose Couchbase:
Fintech & Fraud: a Rose with Thorns
Against the backdrop of the fintech boom shaking up the financial world, fraud is an ongoing challenge for financial services due to the growing opportunities to exploit the less mature technical infrastructure of many fintech startups. For example, it’s easier for fraudsters to open an account using fake identification documents when there are no physical branches. Already costing the global economy £3.89 trillion (around $4.5 trillion in USD), the impacts of financial fraud are only set to worsen unless fintechs implement the right technologies.
Added to the increased opportunities is the fact that detecting and preventing fraud can be an expensive, labor-intensive process for online fintech startups since they often lack the extensive fraud departments and call centers of traditional banks. This is why Revolut needed a fully automated system that could identify fraudulent transactions, notify customers, and allow or block payments without human intervention.
Enter Sherlock, Enabled by Couchbase NoSQL
Revolut developed Sherlock, a machine learning-based card fraud prevention system, to counter the growing threat of financial fraud. Continuously and autonomously monitoring customers’ transactions, Sherlock evaluates these transactions in less than 50ms. If it deems a transaction suspicious, it blocks the purchase, freezes the customer’s card, and sends a push notification prompting the customer to confirm whether the transaction was fraudulent or not. If the customer responds that it was legitimate, the card is unblocked, and they can simply repeat the purchase. However, if the customer doesn’t recognize the transaction, the card gets terminated and they can order a free card replacement.
The awards organizers particularly praised Sherlock for its “really positive solution with clear cut metrics” and the fact it can be “easily integrated to other banks to replicate the efficiency.” And powering Sherlock is our very own in-memory NoSQL database, in which user and merchant profiles are stored and ready to be retrieved at the moment of evaluating whether a transaction is fraudulent or not.
Having tried its luck with other vendors and finding their databases ran too slow, Revolut ultimately chose Couchbase due to its inherent architectural advantages, which meant speed and agility would never be a problem. Scalability was another big selling point: due to the data on users and merchants often changing, Revolut needed a database that could react quickly to changes in size and demand. This is in addition to the ease of maintenance offered by Couchbase, plus the resistance to failure. With millions of documents stored on the database, Couchbase can quickly replicate to another node if one goes down. As Revolut’s FinCrime Product Owner, Dmitri Lihhatsov puts it: “We’ve been using it in production for over a year now. As the number of Revolut users and transactions has been growing, Couchbase has never failed us.”
The results of such innovation have been astonishing: thanks to Sherlock’s performance, more than $3 million per year of customers’ money is saved through preventing fraudulent transactions, with just 1 cent out of every $100 lost due to fraud – compared to an industry average of around 7-8 cents. As Revolut seeks to turn Sherlock into a product that can be purchased and integrated by other banks and financial institutions, we can’t wait to see how NoSQL can help the whole industry fight back against fraudsters.
For more information about Sherlock and Couchbase’s role in its performance, please read:
Enterprise Management 360: Revolut: Machine Learning and Fraud Detection
Congratulations to Revolut and the broader Couchbase team on this recognition!