Instagram Improves Engagement by Reducing Notification Fatigue with New Ranking Framework
Briefly

Instagram Improves Engagement by Reducing Notification Fatigue with New Ranking Framework
"Meta has implemented a new machine learning framework for Instagram that applies diversity algorithms to reduce repetitive content while maintaining user engagement. The diversity-aware ranking system addresses overexposure to similar content creators and product types by introducing multiplicative penalties to existing engagement models. The framework tackles two primary problems: excessive messages from the same content creator and overemphasis on single-product surfaces like Stories while neglecting Feed or Reels content."
"The new system operates as a diversity layer on top of existing engagement models. Notification candidates are evaluated across multiple dimensions, including content type, author identity, notification category, and product surface. For candidates deemed too similar to recent notifications, the framework applies calibrated multiplicative penalties that reduce their relevance score. A demotion multiplier, ranging from 0 to 1, adjusts the base score and lowers the rank of redundant notifications."
"Instagram's machine learning models were previously optimized primarily for click-through rates and engagement metrics, which led to users receiving repetitive messages that could feel spammy and prompt disabling. The real challenge lies in finding the right balance: How can we introduce meaningful diversity into the notification experience without sacrificing the personalization and relevance people on Instagram? The new system operates as a diversity layer on top of existing engagement models."
Instagram implemented a diversity-aware ranking framework that reduces repetitive notifications by applying multiplicative demotion factors to existing engagement scores. The system targets excessive messages from the same creator and overemphasis on single-product surfaces such as Stories, Feed, or Reels. Notification candidates are evaluated across dimensions including content type, author identity, notification category, and product surface. Candidates deemed too similar receive calibrated penalties that lower their relevance. A demotion multiplier between zero and one multiplies the base relevance score to adjust ranks. Engineers can configure per-dimension weights to tune the tradeoff between diversity and personalization.
Read at InfoQ
Unable to calculate read time
[
|
]