Etsy~4 min read

What does personalization miss that curation can provide?

Personalization was working. Quality was not. Shoppers wanted to know a person had picked this, not just an algorithm.

  • Role: Product design and research
  • Timeline: Multi-phase
  • Team: Merchandising, analytics, me
  • Impact: 20% conversion, read over 2 days
  • Platform: Web
The Editors' Picks page: a seasonal “Fall Entertaining and Decor” collection above a grid of curated category tiles.
The dedicated editorial page. A season, a point of view, and an Editors' Picks label, kept off the personalized main page.

Personalized was not the same as curated

Etsy’s recommendations were personalized, but not curated, and shoppers kept saying the quality was not there. The company believed the algorithm had it covered. For 60% of users, it did not.

Ten paper-prototype interviews shifted that view. The finding was specific: personalization says something is relevant to you; curation says someone with taste chose it.

That led to two decisions: where curation should live, and who should be able to publish it. I lost the first and won the second.

What I owned

I owned

  • Design end to end, across the editorial page and the main-page banner
  • Ten paper-prototype interviews, which moved the internal assumption about the algorithm
  • The argument for rule-based authoring over SQL
  • The staged build of the merchandising tool: preview, filters, tagging and themes, then ordering

Shared with Merchandising and Analytics

  • What a collection needed to contain
  • How performance was read after launch: Analytics owned the measurement, including the two-day window

Problem

What happens when a marketplace has no way to put a point of view on the page?

There was no way to surface contextual content to a given audience. Shoppers received personalized, uncurated results that kept missing the quality bar they expected. Product quality and what the site chose to surface were among the larger pain points customers raised.

The obstacle was a belief, not a system. The company held that the algorithm already delivered quality. Ten paper-prototype interviews found that it did not for 60% of users, and that shoppers wanted both: personalization for relevance, curation as proof an expert had chosen this.

Could merchandisers publish without SQL?

Rule-based authoring for merchandisers

Merchandising needed to build and update collections without engineering support. Engineering-built collections required a ticket; SQL offered total expressive power without one, but required the merchandising team to become technical to use its own tool. The PM wanted SQL. We chose less expressive rule-based conditions that a merchandiser could use without help. Removing the engineer also removed the last person who would have read a page before launch, so a wrong rule could reach the homepage banner as quickly as a good one. Rules based on tags and themes could still produce a wrong collection, but not an incoherent one; curation is editorial work, and editorial has always been published by non-engineers. Merchandisers published ad-hoc collections without an engineer, keeping collections changeable rather than ticket-bound.

A second Editors' Picks collection, “Black-owned Etsy shops”, in the same page shell as the seasonal one.
The same shell, a different collection, published without an engineer. That is the rules-over-SQL argument made concrete.

Curation got its own front door

An editorial page with a main-page doorway

Curated picks could be blended into the personalized feed, given a separate editorial page, or made a filter on existing results. The main page drove revenue, and displacing personalized results with editorial ones put that at risk without an upside we could quantify in advance. We kept them separate: curated collections received an editorial page, with a main-page banner as the doorway. That left shoppers to choose to visit, while a blended feed would have put curation where they already were and could have changed behaviour at scale. The banner was a weaker substitute for placement in the feed. The separate page shipped and converted; this project did not establish whether the blended version would have converted better.

Wireframe explorations blending curated picks with dynamic recommendations.
The blended direction in a card system that worked across desktop and mobile. This is the version that did not ship.

What we shipped instead

An editorial page for curated collections, a banner on the main page, and the merchandising tool behind both. We built it in stages: an algorithmic preview; filters that assembled a product mix from shopper behaviour; tagging and themes; then control over ordering.

The tool also supports audience segmentation and prevents someone in two campaigns from receiving duplicate emails.

What the first read showed

0%

Conversion

0%

Engagement

Read over a two-day window on Etsy’s internal analytics immediately after launch, by the analytics team rather than by me. That is the shortest measurement period behind any number on this site, and short enough to have caught a launch rather than a habit. Treat both figures accordingly.

The 20% conversion figure may mostly be a launch spike

The version I wanted put curated picks and personalized recommendations on the same surface, where shoppers already look. It did not ship. Displacing personalized results on the main page risked revenue, and my case for a blended feed was not strong enough against a page already doing its job. We shipped the separate editorial page and its main-page banner.

The 20% conversion and 80% engagement figures came from two days immediately after launch. I do not know whether they reflect the feature or the novelty of a new page on a site people visit often. I would not use those two days to decide that the blended version was the wrong bet.

Sam Cusano