How HSN used AI to get personal with shoppers

The Home Shopping Network was a victim of its own success.

Its reach had expanded across innumerable digital platforms—but while this generated reams of data about its customers, HSN’s marketers struggled to keep track of individual retail journeys.

To up its odds of driving conversions, the company needed to better understand its individual customers, from their unique tastes to their browsing habits. To make that possible, HSN knew it had to automate and accelerate data collection across its channels. It also had to deliver that data to marketers in an organized, easily understandable format that enabled them to take action quickly.

So HSN turned to IBM Watson Marketing. Here’s how it flipped the challenge of a fragmented media landscape into an opportunity for a rich, personalized, cross-platform conversation with consumers.

Wrangling a fragmented conversation
You probably know it for its flagship TV network, but HSN is also active across every major social media platform and boasts a robust email marketing operation.

“As today’s customers choose to engage with us on more channels than ever, it’s vital for us to make that storytelling experience seamless and consistent across all our touchpoints,” said HSN’s SVP of strategy insights and analytics. HSN wanted to take a sequential, conversational approach to the personalized messages it sent consumers, but reconciling the signs and signals from customers bouncing from channel to channel before making a purchase was a time-consuming chore.

To make matters more tedious, HSN had to develop its audience segments by manually slicing and dicing gigabytes of data in Excel.

“Imagine there are 20 different data sources that you’re using to find where your customers are interacting with your brand, and what their sentiment is within your social channels,” said Michael Bordash, engineer for IBM Watson customer engagement.

To make things more efficient, the company’s marketers needed help.

Gaining a cognitive advantage
The goal was clear: engage directly with individual consumers to drive more purchases. The challenge centered on a few question: Which products are most likely to appeal to which specific customers? Which are the best channels on which to surface those products? And finally, what kind of messaging is most likely to lead to a purchase?

To answer them, HSN implemented IBM Watson Marketing’s cognitive marketing platform across all its channels. Cognitive systems have a few key advantages over the marketing platforms most professionals are used to, namely the ability to make sense of a company’s data to truly understand the business and reason their way to effective recommendations, all guided by an underlying machine learning process.

“The aim was to take down the walls between our channels, and we looked for a way to turn our boundaryless retail vision into a reality,” said an HSN representative.

Fill out my online form.

This cognitive system got to work unifying and augmenting the efforts of dozens of different platforms, collecting mountains of information from across HSN’s disparate channels—data such as pageviews, browser and search histories, customer profiles and device type. Then Watson Marketing cleaned and presented the findings in a meaningful, digestible and searchable format.

HSN marketers could then use this platform to create targetable segments, like high-income East Coast women between 28 and 34, a key consumer profile for fashion brands.

Best of all, Watson Marketing presented that information at a moment’s notice, allowing HSN marketers to easily query the platform for the desired demographics. The resulting picture would be built upon all relevant information that HSN had ever accumulated on the target in question across every channel and touch point.

HSN’s secret weapon: Context
The company had gained a granular understanding of customer behavior and attitudes down to their product and content preferences and even which channels they preferred. “We have a picture of the whole customer,” said a representative of HSN. Now, finally, it could initiate and maintain more personalized conversations with consumers throughout their journey.

Countless human behaviors, processed in milliseconds, are now fed to HSN’s marketers in real time, providing a valuable, previously unattainable layer of context based on things as specific as whether certain consumers are more likely to click on a push notification while commuting from Connecticut to New York, or if they don’t read any email promotions after 5pm.

These insights allow HSN to push past hypotheticals and speak to individual customers at the right moments, on the right platforms, and with the right messages—with certainty.

Completing the journey: The human factor
When you’re bogged down in data from a multitude of different platforms, “you’re spending less time on what humans are really good at: Ideation, making content, and creating better interaction channels between humans,” said IBM’s Bordash.

In taking on the analytical and automatic processes best handled by machines, Watson Marketing freed HSN to visualize and act on the results. From there, the humans took the wheel, dreaming up inspired campaigns with unprecedented focus on the behaviors and preferences of specific consumers, tailored to where they were in their specific journeys.

“By making the customer’s journey as smooth and straightforward as possible, we dramatically increase the likelihood of conversion,” said HSN’s director of omni-channel marketing strategy. And for a multi-platform retail company, nothing could be more welcome.

You can withdraw your marketing consent at any time by sending an email to Also you may unsubscribe from receiving marketing emails from IBM by clicking the unsubscribe link in each such email. More information on IBM processing of your personal data can be found in the IBM Privacy Statement [link:].

More from Digiday

Sliders test article

Agencies hope connected TV and digital out-of-home will play a bigger role in upcoming elections and politics — especially for smaller media agencies that are handling many of the less visible races in the crowded political space. For a number of media agencies looking to place their political ad dollars down in this major election […]

How CTV and DOOH are growing this political season for smaller agencies

Connected TV and digital out-of-home are playing a bigger role in upcoming elections and politics – especially for smaller agencies looking to place clients’ dollars.

CMO Strategies: Advertisers identify the top attributes on ad-supported streaming platforms

This is the third installment in Digiday’s multi-part series covering the top ad-supported streaming services and part of Digiday’s CMO Strategies series. In this report, we examine which ad attributes matter the most to marketers on streaming platforms.