Posted on March 7, 2018 by staff

Ocado deploys AI to catch fraudsters

Ocado deploys AI to catch fraudsters

Ocado also uses machine learning to improve product recommendations and search results
Ocado also uses machine learning to improve product recommendations and search results

Ocado, the world’s largest online-only supermarket, is using cloud and machine learning technologies to detect and tackle fraud.

The retailer’s technology arm, Ocado Technology, has developed what it believes to be the world’s first artificial intelligence (AI)-based fraud detection system for online grocery purchases.

The system relies on an advanced machine learning algorithm, and has already improved Ocado’s precision of detecting fraud – any instance where an order is delivered but not paid for – by a factor of 15. 

“Fraud can happen as a result of a genuine mistake (a customer entering the wrong personal details or using an expired card accidentally) but, occasionally, it can also be the result of malicious intent,” Ocado said in a blog post announcing the new system.

“If left unchecked, fraud can propagate to other systems and companies and affect our customer service.

“Therefore, we needed a clever way of predicting and recognising these incidents among millions of other normal events. The answer to this complex challenge was to use the cloud and machine learning (ML).”

In addition to detecting fraud, Ocado has also deployed artificial intelligence into its customer service model, with a machine learning software automatically categorising incoming emails instead of employees having to do this manually.

The company said the motivation behind using machine learning for fraud detection was twofold: speed and adaptability.

“Machines are fundamentally more capable of quickly detecting patterns compared to humans,” Ocado said. “Also, as fraudsters change their tactics, machines can learn the new patterns much quicker.”

The new system has been hailed as “a great success” but Ocado stressed that it was keen to continue improving.

“We are now tackling our next challenges: investigating algorithms that could allow us to explain our predictions in more detail, assessing whether we can transfer learnings from one retailer to another, and considering what tools could help us to streamline our process.”

Enjoy extra content and videos in the interactive digital magazine below

E-edition cover