Features
Recommendation systems timeline without dates: item, profile, and generations
An undated account of recommendation systems: the states an item passes through, the states a profile passes through, where the two lines cross, and generations.
Section
Features
Features
Why there is no honest list of ranking signals, and the four stages instead
Why nobody can give you a list of ranking signals, plus the four jobs every ranking system has and how to read a symptom back to the stage it belongs to.
Features
Ranking signals updates under review: the good, the weak and the verdict
Ranking signals updates under review, ranked: the ones with published documentation, the ones resting on inference, and the verdict on each.
Features
Trend reports: six places where measurement tools diverge
Trend reports: the six design choices that make measurement tools disagree, why the sample is the deep problem, and what to check before quoting a figure.
Features
How viral trends spread: the ratio, the S curve, thresholds
Viral trends trends 2027: the reproduction ratio, why growth is bounded by an S curve, thresholds, and the two exposure mechanisms people confuse.
Features
Recommendation systems: cold starts and feedback loops
How recommendation systems use content and behavior evidence, handle cold starts, and create feedback loops across YouTube, TikTok, and Instagram.