When you’re searching for a specific outfit, words are often not enough to find exactly what you need.
In J.Crew, the searching experience is a crucial part of our e-commerce cycle and for that reason we wanted to connect customers precisely with what they’re looking for through better search, using exclusively images.

How can we do this?

Visual search specifically refers to the technology that carries out pixel-to-pixel comparisons between images in order to generate visually similar results. The user provides images to return visual matching content across the website. To make this happen, we partnered with a vendor that provides Artificial Intelligence solutions, helping us to create specific models and prediction concepts that would be integrated through an API into our system. My task was collecting initial data to understand how this new tool would interact with our customers, to create wireframes explaining the UI and to provide precise prototypes for our software engineering team.

My Role:

I designed the search experience between September 2017 and February 2018 and I worked alongside Creative stakeholders, 1 Product Manager, 1 Project Manager and 2 developers. I stopped working on the project once the UI was defined, although I continued being involved in the engineering and vendor meetings.
The project was put on hold with the foresight to launch in March 2019.