Netflix's GenRec: An LLM-Native Ranker Beats Production with 40x Less Data
GenRec: Towards LLM-Native Recommendation at Netflix
Netflix introduces GenRec, an LLM-based recommendation ranker that post-trains an internal foundation model on Netflix-specific data and objectives. By verbalizing user histories and item metadata into natural-language prompts, GenRec reduces reliance on hand-engineered features, shifting focus from feature engineering to context engineering. In a large-scale A/B test, GenRec achieved statistically significant improvements in both short-term and long-term metrics over a mature production ranker, despite using roughly 40x fewer labeled examples and input signals. The system runs in prefill-only mode on Netflix's LLM serving stack for cost efficiency.
In a large-scale A/B test against a well-tuned production ranker, GenRec achieves statistically significant improvements in both short-term and long-term online metrics, while using only a small fraction of the Phase-2 labeled data and input signals.
- lqstuart
Netflix has imo the worst recommendations on the entire internet. They are a Java shop that’s 5-10 years behind the industry in AI, and now they’re trying to use the most grossly inefficient and overcomplicated method out there to try to be trendy instead of just using a DLRM like everyone else was in 2020. What could go wrong?
- mvkel
Netflix had an algorithm contest, when was it, like 20 years ago? A team made a highly effective content recommendation system and Netflix never used it. Why? It killed revenue.
Separately, there simply isn't enough content to recommend. It's not like you need help finding the perfect Wikipedia article. At any one time, there are ~50 things a user would probably watch.
Feels more like a soft pivot to cash in on AI valuations since Hollywood is cratering. Probably worth the investment.
- alt227
Here we go, the start of LLMs plugged into everything.
Do Netflix recommendations really need to use LLMs?
This post paints a very altruistic picture of how recommendations can be fed from user history, preferences, device and environment context etc. However they make no mention of needing to advertise content from paid clients, promote new releases, and increase views on certain underperforming content. I'm assuming that once their fancy LLM spits out some user recommendations, they are then run through another process to 'commercialise' the results before displaying them to the user.
- chuckadams
How much advanced machine intelligence does it take to not put stuff on the recommended list that they know I've already watched?
- jmbwell
Okay. Well so if the model will tend to converge on the median of a user’s interests as measured by engagement… the user would have to depart from the recommendations to increase the odds of being recommended something surprising, no?
It’s interesting to see how Netflix evaluates RecSys internally, inferring from how they are comparing GenRec to it. In both cases the premise seems to be that users mainly want to engage with more of the same.
I would be even more interested in some kind of comparison to Netflix’s much earlier system for exchanging reviews and recommendations among a user’s human social group. Seems like there could be some insights around the input of fresh signals from aligned but not strictly conforming participants.