marketing_ops · workflow

Nextdoor uses ML and PID-controlled budgets to send relevant notifications to neighbors

Nextdoor's legacy heuristic notification system sent updates to a random sample of eligible neighbors with no ability to understand why a particular notification might be relevant to a specific person.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · New or trending post triggers pipeline
A newly created post or a post gaining conversation triggers the notification pipeline to identify neighbors to notify.
Tools used
XGBoostredis
Outcome

For the same notification volume, the ML system produced up to a 40% increase in email click rates and a 23% increase in push tap rates compared to the legacy system, contributing to an 8% overall increase in daily active neighbors.

What failed first

The first ML-based threshold estimation method used historical score distributions (via Q-digest) to predict notification cutoffs, but was sensitive to score tail noise, carried a bias from single-post multi-scoring, and could not recover quickly after pipeline outages.

Results
Volumeup to 40%
Running sinceover a year
Source

https://engblog.nextdoor.com/nextdoor-notifications-how-we-use-ml-to-keep-neighbors-informed-57d8f707aab0

How we source this →

Grounding & classification
Source type: technical build writeup
19 fields verified against source quotes, 1 dropped as unverifiable.
personalizationpredictive analyticsrecommendation systemsocial media postfailure mode describedmetric backednamed customerproduction runtime claimedsource backedtools describedsoftwareconversion increasecustomer satisfactiontechnical build writeupmarketing opsextract classify routemonitor detect alert