You may be overrating what they do. I suspect that 90% of the recommendation wei... | Hacker News

Hacker News new | past | comments | ask | show | jobs | submit

login

mathattack on Nov 24, 2020 | parent | context | favorite | on: You might not need machine learning

You may be overrating what they do. I suspect that 90% of the recommendation weight is based on what other people clicked after watching the same video.

sidlls on Nov 24, 2020 [–]

I've seen so many really complex real-time recommendation pipelines that could be replaced by a simple weighted click-rate style algorithm.

The application of ML and data science in this industry is quite hilariously bad, really.

mathattack on Nov 24, 2020 | [–]

Somehow so much leads to correlation. :-)

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact