GenPage: Towards End-to-End Generative Homepage Construction at Netflix
For Netflix, this demonstrates a viable end-to-end generative alternative to a mature, highly optimized production system, though the engagement gain is small.
GenPage replaces Netflix's multi-stage recommender stack with a single transformer that generates the entire homepage autoregressively. In online A/B tests, it achieved a +0.24% lift in core user engagement (p<0.001) and reduced serving latency by 20%.
We present GenPage, an end-to-end generative approach to Netflix homepage construction that replaces the traditional multi-stage recommender stack with a single transformer. GenPage treats the user and request context as a prompt, and autoregressively generates the entire structured, multi-row homepage as the response. We adapt the LLM training recipe: pretraining on production pages, followed by post-training via weighted binary classification (WBC) or reinforcement learning (RL). For industry-scale deployment, we introduce techniques addressing cold start, model freshness, business-rule enforcement, and serving efficiency. In online A/B tests against a mature, highly optimized production homepage recommender, the WBC variant of GenPage delivered a +0.24% lift on the core user engagement metric we use for launch decisions (p < 0.001), while reducing end-to-end serving latency by 20%. Offline, two findings stand out: enriching the prompt yields a larger improvement than scaling model capacity in our current regime, and RL post-training increases homepage diversity even though diversity is not part of the objective.