Visa Harnesses AI Tech To Reduce Declined Transactions

The new tool allows transaction approvals to be made based on individual cardholder history.

Thanks for subscribing!

Need to Know

  • Visa Smarter Stand-in Processing (Smarter STIP) is a new capability that uses AI tech to help banks manage authorizations when service disruptions occur.
  • This tool will allow financial institutions to make a transaction decision if user cards are declined due to scheduled maintenance or an unexpected outage.
  • Approvals will be made by an AI tool that can analyze a cardholder’s past transactions.
  • The new tool will be available in October 2020.

Analysis

Visa is adding a new AI tool that will help banks authorize credit card transactions that are declined due to service disruptions, the company revealed on Wednesday.

The Visa Smarter Stand-in Processing (Smarter STIP) tool lets banks make decisions to allow transactions from customers whose cards are declined due to scheduled maintenance or an unexpected service outage. The AI tool analyzes a customer’s past transactions in order to make the call: Visa’s new Smarter STIP tool makes approval decisions based on individual cardholder data, rather than on the accumulated information available about a specific card portfolio. This is expected to reduce call-times to Visa’s customer service line, as well as reduce transaction declines for cardholders by up to 50% in some cases.

“AI is one of the most transformative technologies of our time, giving us the power to build data-driven products that deliver new levels of insight and personalization,” Rajat Taneja, president of technology at Visa, said in a press release announcing the new tool. “With one of the largest and richest data sets in the world, Visa is extremely well-positioned to unlock the full potential of AI for our clients and cardholders, and at massive scale.”

Visa’s new tool improves on existing STIP capability through real-time evaluation of cardholder-level information. The technology uses billions of historical records and apparently produces a 95% accuracy rate in emulating a cardholder’s behavior. It also leverages real-time transactions and outage data to continually learn and adapt.

“We’ve made significant investments in our infrastructure, making it possible to harness this data more deeply across all facets of VisaNet,” Taneja said, referencing the company’s global payment network. “Our data, combined with low-latency architecture and our unique modeling capabilities, make our technology platform among the most powerful for AI.”​

Visa has been continually investing in AI tech to improve the experience of both vendors and individual cardholders. In 2019, it was reported that its use of Visa Advanced Authorization, which leverages machine learning, has prevented roughly $25 billion in fraud. The company has been utilizing some form of artificial intelligence since 1993 when it became the first payment network to apply neural network-based machine learning to its transactions.

The company has also been bolstering its technological capacities in other areas, as both vendors and consumers look for more seamless, digitally-focused ways to process payments and transactions. In February, the company revealed it would be introducing simpler ways to pay with Visa, including click-to-pay options online. At the time, the company also outlined a plan to embed digital wallets through IoT integrations in vehicles, appliances, and other consumer electronics.

And as more consumers are gravitating towards buy now, pay later financing options with instore and, largely, online purchases, Visa has recently partnered with field-leader Splitit to expand such capacities to cardholders and merchants looking to expand their payment plan options.

The implementation of Visa Smarter STIP does not any action on the part of cardholders or clients. Vendors that already use Visa debit processing services will be enabled for Smarter STIP when it is made available worldwide in October 2020.

Thanks for subscribing!

Thanks for subscribing!