Designing the future of in-store, real-time personalization
Helping retailers shift from data extraction to value exchange
Role
Design Lead
Duration
7 months, January - August 2025
Team
2 Designers, 1 Researcher, 1 Engineer, 1 PM
Client
ENAiBLE, Carnegie Mellon University’s retail collective
Essential Question
What is the future of in-store personalization?
Retail is more advanced than ever, yet 90% of shoppers describe in-store shopping negatively, costing retailers $262 billion in lost sales anually.
As a design lead on my work with ENAiBLE, I led the design of Cerulean, an app bridging the gap between retailer and shopper needs.
Cerulean has five key features designed to reduce shopper’s overwhelm and retailers data gaps, the biggest pain points we uncovered.
Apparel retail has an in-store personalization problem. Both shoppers and retailers want it, but neither is getting it.
Through interviews with 20 retailers and 20 shoppers we learned the following: shoppers are desperately overwhelmed with in-store shopping and retailers know that they are beginning to drown in the noise of products.
Both know that personalization is the answer – digital personalization has demonstrated huge gains in profit for retailers. Shoppers also want personalization – 75% of consumers want personalization to make it easier for them to navigate in-store*. Yet, neither shopper nor retailer is getting the personalization they want. *McKinsey & Co Next in Personalization 2021 Report
"Shopping in-store is.. overstimulation... I get really antsy as well if I can't find something, and I'm like, looking and looking and looking, I'm just like, okay, there's no point of me being here let's move on.."
– 25 year old female shopper
In-store personalization is being blocked by an absence of data to make it happen.
Through follow-up interviews with retail SME’s, we learned that retailers are very data starved when it comes to in-store shopping. As such, they’re trying to gather data from customers through every means possible.
This, in turn, is leaving shoppers exacerbated and their true needs unattended. Shoppers want tools to support their shopping journey, but instead are receiving overwhelming data requests that don’t seem to provide any value.
“Without a rewards account to associate with a purchase, we miss a very large area of data...65% of the time we do not know who's shopping.”
– UX Researcher at American Eagle Outfitters
The solution *is* data-driven personalization, but not the way that retailers were pursuing it.
Retailers were pursuing personalization from an approach where they extract the most possible data to then create personalized experiences. It was patronizing in nature, rather than value-driven.
But it was also a failing recipe. Shopper data is fragmented, making comprehensive data collection almost impossible for a single retailer.
To narrow in on what we needed to design, we took a look at the shopper journey and pain points.
After a detailed analysis of our journey maps and personas, we chose to hone in on the preparation process. The preparation phase allowed us to leverage existing behavior (80% of shoppers already prep for their shopping before going in-store!) and positively affect the journey downstream.
Preparation
Fragmented + inefficient information gathering
Exploration
Too many options + unclear navigation
Evaluation
Analysis paralysis + exhaustion
Decision
Unintentional purchases
Preparation
Exploration
Evaluation
Decision
We then set out to determine what our product would look like, prioritizing and exploring shopper needs through 30 rapid prototyping experiments.
We prioritized shopper boundaries because we needed to create value for shoppers first to earn their trust and ultimately, data.
The top shopper needs we uncovered were Autonomy, Confidence, and Respect around data sharing. We broked down each need even further, in order to test the boundaries of each.
Control
Choice
Comfort
Info
Identity
Data Request
Creep-iness
Autonomy
Confidence
Respect
After testing concepts through UI wareframes, we arrived at a final set of features through an evaluation of feasibility and impact.
Most of our shoppers preferred ideas which were store-agnostic, helped them make more informed decisions, and supported their in-store navigation through live updates.
With our concept and features finalized, we conducted 3 rounds of usability testing to refine our UI flows, design system, and concept's value.
We conducted intercepts, A/B tests, and moderated usability tests with 20 shoppers. Specifically, we tested for task completion, interest, and error rates.
80% of our final testers expressed a willingness to pay 99 cents to download our app.
Contextual Search
Search that considers shoppers full context to surface accurate, in-stock options across brands.
Search Refinement
Intuitive, Pinterest-like visual process that lets shoppers narrow results based on the details that matter most to them.
Curated Match List
Prioritized, location-aware list showing in-stock items that met budget, size, and context criteria.
Smart Filters
Auto applied filters narrowing results by previous preferences so shoppers don’t have to.
Plan Map
Auto applied filters narrowing results by previous preferences so shoppers don’t have to.
Feel free to explore our live MVP here:
Our solution was designed for both shoppers and retailers.
Although we prioritized shopper needs in our visual design, our strategy always included retailer needs. Throughout the process, we consulted with 8 major retailers constantly, ensuring that we were keeping their constraints in mind.
While we ran out of time to pressure test willingness to implement our solution, we did gauge retailer interest. Retailers at five major companies, including Walmart and American Eagle Outfitters expressed wanting to learn more about our solution through a follow up meeting.
Thank you for reading!
I am happy to talk about the process of developing Cerulean in depth in-person!
Ashley Sánchez
Thanks for stopping by!
