How Narvar uses AI and data to improve the post-purchase customer experience

What happens after a customer clicks the “Buy” button on an eCommerce website?

It’s an area called “post-purchase” and is often one of the most costly and impactful aspects of business operations for retailers. Post-purchase activities include determining delivery, customer loyalty and, if necessary, returns. One of the pioneers in this field Narvar which counts more than 1,500 global retailers, including major brands such as Gap, Levis and Sonos among its customers. Across all of its various customer touchpoints, Narvar collects information from more than 42 billion consumer interactions annually.

Today, Narvar is expanding the intelligence of its services with a new one AI-powered platform it’s called IRIS (Intelligent Retail Insights Service). IRIS combines data, AI and analytics in a highly optimized platform. The goal is to help retailers fight fraud, optimize delivery promises, streamline returns and create more personalized customer experiences. Among the first services enabled by IRIS is AI-powered Narvar Assist, which aims to automate claims management and help reduce fraud in delivery claims.

Early results from a cohort of 20 retailers show dramatic improvements: an 80 percent reduction in fraud inquiries and a 25 percent reduction in appeasements, or compensation, awarded by retailers for shipping-related issues.

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

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

Kumar joined Narvar in 2021 as Chief Customer Officer and became CEO in October 2024. Previously, she spent a long time working in customer service at Levis Strauss and Co., Walmart and Target, where she saw firsthand the challenges facing retailers.

Retailers of all types generally spend a lot of time and effort thinking about customer acquisition. Kumar noted that the big challenge, however, is retaining customers.

“Post-purchase, it’s really about thinking about what the next challenges are to keep your customers coming back and really treating them the way they need to be treated and giving them personalized experiences,” she said.

With all the data Narvar collects, AI is now able to help retailers turn the post-purchase period into an activity that helps build customer loyalty. The use of AI in retail has been difficult overall; for example, a Forrester 2024 report There was great interest, but acceptance was low.

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

How Narvar uses AI to improve the bottom line

The IRIS system uses a combination of AI and Google Cloud data servicesas well as proprietary machine learning (ML) and predictive AI algorithms.

Narvar CTO Ram Ravicharan highlighted the power and importance of the data the company has AI to help retailers. Narvar processes billions of consumer touchpoints, providing unique insights into customer behavior and intent.

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 transactions that people make along 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 the way we look at it.”

With predictive AI models and the data, Narvar has a solid understanding of customer intent. This can be extremely useful for both customer retention and fraud prevention.

Beyond combating fraud, IRIS is also designed to help retailers make more accurate delivery promises and strengthen customer loyalty. Before IRIS, Narvar typically relied on rules-based models, particularly for commitments such as estimated delivery date. With the new models, there is more information from across the retail network to ensure a higher level of accuracy, Kumar noted. For example, the system detects weather issues and carrier delivery systems that may impact delivery.

“Everyone focuses on customer acquisition, but they lose them and pay to win them again,” Kumar explained. “IRIS helps retailers build lasting relationships by delivering personalized experiences right when they matter most – after the sale.”

Early adopters are seeing benefits

Narvar Assist technology is not yet widely available, but is being tested by existing customers.

Below is Boston Proper. The clothing retailer has been a Narvar customer for six years, said Boston Proper CIO DeAnne Judd. To date, Boston Proper has used Narvar’s Engage solution to proactively notify consumers about the delivery of their orders and possible exceptions, improving visibility and customer experience. The company also uses Narvar’s returns and exchanges solution to automate return processing and provide consumers with visibility into the status of their refund.

Judd noted that Boston Proper is currently using the first IRIS solution, Assist, which leverages the Narvar ecosystem to reduce costs due to fraud.

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

Bridging online and physical stores

Moving forward, Narvar plans to expand IRIS in several ways.

While the first Assist product focused on online transactions, Kumar noted that Narvar is working with some retailers to expand in-store capabilities as well. The Narvar platform provides insights into data and interactions across online, in-store and even warehouse operations.

“Our vision is to connect online and in-store environments, and the way we have built our models and the way we develop transaction intent is cross-channel,” she said.