From the archive
Wednesday, 14 October
Folded from 15 sources that day.
Sorted by quality and by how many sources covered it, the same for everyone.
-
Measuring the Impact of Personalized Recommendations
Netflix presents a behavioural model that separates members' underlying tastes from the incremental effect of recommendations, validated with small A/B tests that nudge title salience.
-
DataJunction as Netflix's answer to the missing piece of the modern data stack
Netflix describes adopting the open-source DataJunction semantic layer to replace a slow, complex metric authoring process in its experimentation platform, citing its SQL parsing and graph of definitions.
-
The Self-Organizing Data Stack
Argues that agents make generating pipelines cheap while refactoring stays risky, and proposes treating data assets as stable logical data products with the orchestrator maintaining the dependency graph.