How Narvar uses AI and data to improve customer experiences after purchase

What happens after a customer clicks the “buy” button on an e-commerce site?

It’s an area known as post-purchase, and is often one of the costliest and most impactful aspects of operations for retailers. Post-purchase activities include delivery knowledge, customer retention, and returns if necessary. Among the pioneers in space Narvar Which counts more than 1,500 global retailers, including major brands like Gap, Levis and Sonos among its clients. Across all diverse customer touchpoints, Narvar collects information from more than 42 billion consumer interactions.

Today Narvar is expanding the intelligence of its services with a new system Artificial intelligence platform It’s called IRIS (Intelligent Retail Insights Service). IRIS combines data, artificial intelligence and analytics in a highly optimized platform. The goal is to help retailers fight fraud, improve delivery promises, simplify returns and create more personalized customer experiences. Among the first services IRIS is making available is the AI-powered Narvar Assist service, which is designed to automate claims management and help reduce fraud in delivery claims.

Early results from a group of 20 retailers show dramatic improvements: an 80% reduction in fraud-related inquiries and a 25% reduction in reconciliations, or reimbursements offered by retailers for shipping-related issues.

“We don’t just solve problems; “We are transforming what has traditionally been a cost center into a strategic advantage for retailers,” Narvar CEO Anisa Kumar told VentureBeat in an exclusive interview.

Why AI in post-purchase processes is critical to retail success

Kumar joined Narvar in 2021 as Chief Customer Officer and became CEO in October 2024. Prior to that, she had a long history working in the trenches of customer operations at Levis Strauss and Co. Walmart and Target, where she saw the challenges retailers face firsthand. .

Retailers of all types generally spend a lot of time and effort thinking about consumer acquisition. Kumar noted that the biggest challenge is retaining customers.

“Post-purchase is really thinking about the next frontier to keep consumers coming back, really treating them the way they need to be treated, and giving them personalized experiences,” she said.

Thanks to all the data Narvar collects, AI is now able to help retailers turn a subsequent purchase into an activity that helps retain customers. The use of AI in retail operations in general has faced difficulties; For example, A 2024 Forrester Report It found high levels of interest, but low levels of adoption.

As a SaaS offering, Narvar makes it easier for retailers to capture the benefits of AI. Kumar explained that the IRIS platform will help create highly personalized post-purchase experiences for retailers and end consumers.

How Narvar uses AI to improve the bottom line

The IRIS system uses a combination of artificial intelligence and Data services from Google CloudIn addition to special machine learning (ML) and predictive AI algorithms.

Ram Ravisharan, CTO at Narvar, emphasized the power and importance of the data the company has to inform AI to help retailers. Narvar processes billions of customer touchpoints, giving it unique insights into customer behavior and intentions.

Narvar’s IRIS does not use generative AI, although it does use techniques pioneered in large language models (LLMs), including the use of transformers.

“If you think of the transactions people make in the purchasing journey as a language, we now almost have a language for what the next sentence is going to be,” Ravicharan explained. “And that’s literally how we look at it.”

Thanks to predictive AI models and data, Narvar has a strong understanding of customer intent. This can be extremely beneficial for customer retention as well as fraud prevention.

In addition to mitigating fraud, IRIS is also designed to help retailers make more accurate delivery promises and enhance customer loyalty. Before IRIS, Narvar tended to rely on rule-based models, especially for commits like estimated delivery date. Kumar noted that with the new models, there is more information across the retail network to provide a higher degree of accuracy. For example, the system is aware of weather issues and carrier delivery systems that can affect delivery.

“Everyone is focused on acquiring customers, but they lose them and pay to acquire them again,” Kumar explained. “IRIS helps retailers create lasting relationships by delivering personalized experiences when it matters most – after the sale.”

Early adopters see gains

Narvar Assist technology is not yet generally available, although it is being trialled by existing customers.

Among these Boston proper. DeAnne Judd, IT Manager at Narvar, explained that the clothing retailer has been a Narvar customer for 6 years. To date, Boston Proper has used Narvar’s Engage solution to proactively notify consumers about their order delivery and potential exceptions to improve visibility and customer experience. The company also uses Narvar’s returns and exchanges solution to automate returns processing and provide consumer visibility into the status of their refund.

Goode noted that Boston Proper is currently using IRIS’s first solution, Assist, which leverages Narvar’s ecosystem to reduce costs from fraud.

“Since integrating Narvar Assist, customer communications and costs have decreased due to the improved user interface and streamlined intelligent operations,” Judd said.

Bridging online and in-store

Looking to the future, Narvar plans to expand IRIS in several ways.

While the initial assistance product was focused on online transactions, Kumar noted that Narvar is working with a few retailers to expand in-store capabilities as well. The Narvar platform has insights into data, online and in-store interactions, and even warehouse operations.

“Our vision is to bridge the online and in-store environments, and the way we’ve built our models and the way we’ll develop transactional intent goes across channels,” she said.