Faire
AI / ML EngineerAppliedAug 6, 2026

Diversify product recommendations in first 20 results

Discovery feeds can feel complete while still showing too little variety.

Similarity improves local relevance, but repeated patterns can narrow the buying decision.

I like the style, but after six candles that look alike, I’m done scrolling.

Pranav Mukherjee · Buyer, Home and Lifestyle Store

A retailer using recommendations to find new lines that fit an existing store aesthetic.

What pulls against what

  • personal relevance vs. assortment breadth
  • offline diversity vs. live behavior
  • model complexity vs. serving budget
  • catalog semantics vs. visual similarity

What is at stake

Retailers need inspiration, not a longer list of nearly identical products. Better ranking diversity can expand consideration without sacrificing relevance

Why Faire

Wholesale assortment building often depends on helping retailers find adjacent ideas without making the feed feel random.

Written for

Recommendation engineerRanking ML engineerApplied experimentation engineer

This is the setup. The work is inside.

Running it puts you in the room: the full situation and its constraints, stakeholders who push back in their own words, and the decisions that are yours to make. What you produce becomes a Day One Plan — work you can show someone instead of describing.