# Serendipity: Accuracy's Unpopular Best Friend in Recommenders

DevFeed: [Serendipity: Accuracy's Unpopular Best Friend in Recommenders](<https://devfeed.tech/articles/serendipity-accuracy-s-unpopular-best-friend-in-recommenders-46548.md>)

Original publisher: [Read original article](<https://eugeneyan.com//writing/serendipity-and-accuracy-in-recommender-systems/>)

Author: Eugene Yan

Published: 2020-04-26T00:00:00Z

Content type: article

Language: en

Sources: [Eugene Yan](<https://devfeed.tech/sources/eugene-yan.md>)

Topics: [recommendation systems](<https://devfeed.tech/topics/recommendation-systems.md>), [recommendations](<https://devfeed.tech/topics/recommendations.md>), [data](<https://devfeed.tech/topics/data.md>), [Risk](<https://devfeed.tech/topics/risk.md>)

Tags: [data](<https://devfeed.tech/tags/data.md>), [measuring](<https://devfeed.tech/tags/measuring.md>), [papers](<https://devfeed.tech/tags/papers.md>), [recommendation-systems](<https://devfeed.tech/tags/recommendation-systems.md>), [recommendations](<https://devfeed.tech/tags/recommendations.md>), [recsys](<https://devfeed.tech/tags/recsys.md>), [serendipity](<https://devfeed.tech/tags/serendipity.md>), [survey](<https://devfeed.tech/tags/survey.md>), [training-data](<https://devfeed.tech/tags/training-data.md>)

## AI overview

An analysis of why recommender systems should optimize for serendipity alongside accuracy. It discusses measuring diversity, novelty, and surprise, and explains how broader recommendations can improve customer discovery, assortment health, seller health, and training data.

## Source excerpt

What I learned about measuring diversity, novelty, surprise, and serendipity from 10+ papers.