Know where search management hits limits

I mentioned my experience with Shopify merchants that controlled their own search quality. They manually outperformed our best algorithms.

The average Shopify store is a specific case:

• A handful of popular queries drive outsized sales
• Catalogs tend to be smaller
• Sellers create new products in niche domains

Contrast this with the general Amazon-like megastore

• billions of unique queries
• long tail queries
• huge catalog
• catalog constantly changes
• generic products

Is search management useful here?

Yes but focused on:

• Edge cases - the places general search models fail
• Head queries - very popular queries that absolutely must give right answers
• Not mapping queries to products, but instead mapping to attributes of the ideal product (a category, an image embedding, etc) to ensure they stay general
• Vigilant measurement - the increased user traffic makes it more plausible to measure the impact of rules
• Retiring agressively - force teams to frequently review every instantiation of a manual intervention in search at some period

In this way, you’re patching the important problems, but watching it like a hawk

-Doug

​

This is part of Doug’s Daily Search tips - subscribe here