AI & Machine Learning

4 case studies on how Machine Learning is helping retailers drive revenue

Retailers are eager to apply technology to improve personalization, drive revenue growth, and reduce costs in marketing and operations. A recent report from Juniper Research predicts spending on machine learning in the retail sector will increase by 230% between 2019-2023 and that 325,000 global retailers will be using machine learning in some form by 2023. But what exactly is machine learning? And how are retailers implementing it?

What is machine learning?

Like artificial intelligence (AI – any technique used to create human-style reasoning in machines), machine learning is a computer science term. It is “a subset of AI describing techniques that allow a computer to improve on tasks with experience – using data to train itself, recognize patterns, and make predictions.”

Are companies investing in it?

Machine learning is transforming the retail industry, and some brands are implementing it to gain an edge over their competitors. According to the study by Juniper Research referenced above, 33% of businesses surveyed have implemented machine learning and 24% of Retail/Wholesale enterprises say data science, AI, and machine learning are critical to their success.[2] The study also found that marketing and sales departments are the biggest proponents of machine learning, with 40% in favor of it.

This chart illustrates how brands are applying machine learning:

Image via Slideshare

How are retailers using machine learning?

Here are some real-world examples from companies employing machine learning to impact their bottom-line.


Use case: Improving conversions through personalized product recommendations

eCommerce retailer, 1-800-Flowers, was one of the earliest adopters of machine learning. In 2016, the brand introduced GWYN, an acronym for ‘Gifts When You Need’, an AI assistant powered by IBM.  GWYN interacted with customers and gathered information on the gift recipient, so it could tailor gift recommendations for the occasion. The purpose of GYWN was to recreate the experience of talking to a florist in a brick-and-mortar store. Through these personalized conversations, customers got the expertise and attention they would expect in a face-to-face interaction, while still having the convenience of shopping from home. Chris McCann, the CEO of 1-800-Flowers, said that over 70% of GWYN’s orders have been from new customers, and those customers have skewed younger, giving 1-800-Flowers a new demographic to target.[3]

Image via Retail Customer Experience


Use case: machine learning for language translation

eBay, one of the largest eCommerce platforms in the world, had a language problem. International buyers and sellers were using the platform to connect with each other, but communication presented a barrier to follow-through on business transactions. To help facilitate these transactions, eBay decided to test out a technology they dubbed eBay Machine Translation (eMT). They started with a focus on Spanish/English translations for product titles, with the idea that it would help boost U.S. and Latin American transactions. The eMT system translated product titles with a 90% accuracy rate, trade increased by 1.06 percent for each additional word in the titles of items on eBay and overall commerce increased by 10.9%.[4] After seeing such great results, eBay has since expanded the use of eMT for all their translating needs and started to cover product descriptions and reviews. While this gets tricky when considering the many different combinations of languages as sellers and buyers converge from around the world, eBay is committed to investing in this technology to improve the customer experience. Evgeny Matusov, eBay’s Senior Manager of Machine Translation Science, has said that the reason eMT has been so successful is that eBay has employed some of the biggest names in machine learning and have also included eBay seller jargon as part of the technology. For example, eMT is programmed to understand that ‘NIB’ translates to “new in box” for seasoned eBay users. Ultimately, Matusov stresses that the goal is the improve the user experience. “Machine translation can connect global customers, enabling on-demand translation of messages and other communications between sellers and buyers. It helps them solve problems and have the best possible experiences on eBay.”[5]

Image via eBay Inc.


Use case: Optimized route planning for improved customer service and lowered supply chain costs

Brewing company, Anheuser-Busch utilized machine learning to improve their delivery routes. The company rolled out a pilot program in two different cities to test a machine learning platform. They collected data such as weather, traffic, customer location, driver satisfaction, driver experience level, optimal times for parking and customer delivery. The machine learning technology used this data to recommend the best routes (based on time and cost savings) – taking into account the delivery preferences of customers and the experience level of their drivers. After implementing the optimized routes, the company saw an increase in customer satisfaction, employee satisfaction, and lower costs. The results were so significant, that they implemented machine learning nationwide.[6]


Use case: Detecting life events to improve customer experience and increase sales

Big box retailer, Target, used machine learning to detect when customers were about to become new parents, in order to offer essential items for the new addition to their family. Target hired machine learning expert, Andrew Pole, to create technology that could predict when someone was pregnant by analyzing common purchases made by customers shortly before they opened a baby registry. The technology was not only able to predict pregnancy, it could pinpoint which trimester the customer was in. For example, a purchase of unscented lotion could indicate the woman was at the start of her second trimester. Target used this data to personalize messaging and create relevant offers, so customers have what they need during pregnancy and beyond. Target also sent coupons for the most commonly purchased products to pregnant customers, helping cement their loyalty to the brand.[7]

Image via Instagram


As market changes disrupt the retail industry, savvy brands are applying machine learning to improve the customer experience, streamline operations, and increase sales.


Natasia Langfelder
Content Marketing Manager

As Content Marketing Manager, Natasia is responsible for helping strategize, produce and execute Data Axle's content. With a passion for writing and an enthusiasm for data management and technology, Natasia creates content that is designed to deliver nuggets of wisdom to help brands and individuals elevate their data governance policies. A native New Yorker, when Natasia is not at work she can be found enjoying New York’s food scene, at one of NYC’s many museums, or at one of the city’s many parks with her two teacup yorkies.