[Top System Design Case Study Pulse #38] How Facebook's Notification Engine Decides When to Wake Up Your Phone — How Push Notifications Actually Works : Deep Dive from System Design Perspective

A Deep Dive into Meta’s ML-Powered Push Notification Ranking, Timing Optimization, and Engagement-vs-Wellbeing Tradeoff System Using the ML System Design Framework..

In this post we will take a deep dive into Meta’s ML-Powered Push Notification Ranking, Timing Optimization, and Engagement-vs-Wellbeing Tradeoff System Using the ML System Design Framework , we will cover —-

---

Table of Contents

1. Clarifying Requirements

2. Frame the Problem as an ML Task

3. High-Level Architecture

4. Detailed Components Design

5. Data Preparation

6. Model Development

7. Evaluation

8. Serving

9. Trade-off Discussion

10. Failure Scenario Discussion

First let me share the stats - 420000 views and reads in past 65 days! Our readers love How to System Design Series and on their demand we are giving mega discount for everyone. Yayyy!

You can also gift subscription to your friend if they are in need or would like to read how to system design or preparing for interviews!

We will covering more than 75+ top and most asked system design case studies in depth — not just to prepare for system design rounds but also to understand how large systems work.

To Celebrate From Our side : Straight 80% off Discount Code for all the System Design Posts and Code : Link

Straight 80% off Discount Code for all the AI inference, AI optimizations and Evals Posts and Code : Link

Top System Design Viral Playlist : Link

Top ML System Design Viral Playlist : Link

Full Access: [Important Bookmark : Smartest System Design Roadmap ] Best and Shortest Plan : How to Prepare and Ace Any System Design

---

Read and Access all the Top and Most Asked System Design Case Study Posts :

[Important : Generative AI System Design #2 ] AI vs. ML vs. Generative AI: Understanding the Nested Relationship and Discriminative vs. Generative Models — How it Actually Works

[Top System Design : Engineering Postmortem #36] How One Faulty Update Bricked 8.5 Million Windows Machines Overnight: Deep Dive from System’s Design Perspective

[Top System Design : Engineering Postmortem #35] How Automated Trading Algorithms Erased $1 Trillion From the Stock Market in 36 Minutes: Deep Dive from System’s Design Perspective

Black Monday : How a Network Upgrade Locked Slack’s Own Engineers Out of Their Own Systems : Deep Dive from System’s Perspective

[Important : Generative AI System Design #1 ] From Transformers to Trillion-Parameter Systems : The Complete Generative AI System Design

[Important Bookmark : Smartest System Design Roadmap ] Best and Shortest Plan : How to Prepare and Ace Any System Design

How Does Google Reverse-Image Search Map 100 Billion Images Into High-Dimensional Vector Spaces? — How It Actually Works

The Day Facebook Deleted Itself: Inside the 6-Hour BGP Catastrophe of October 4, 2021

How One Bad Regex Rule Took Cloudflare System Down for 27 Minutes — and Broke Half the Web

How One Mistyped Command Took Down 150,000+ Systems for 4 Hours

How a GitLab Engineer Deleted 300GB of Production Data in 2 Seconds

Trillions of Edges: How Facebook Builds Your News Feed in Milliseconds — How It Actually Works

You Hit Upload & 30 Seconds Later More than 1 Million People Can Watch It: TikTok’s Video Pipeline Processes Every Upload in Real Time— How It Actually Works

Millions of Packages: How Amazon Prime Delivery Routing Achieves Next-Day Perfection — How It Actually Works

Millions of Swipes and Matches: How Tinder’s Real-Time Hidden Matchmaking Actually Works

Is YouTube’s “Up Next” Loop Reading Your Subconscious? Inside the Deep Candidate Generation Architecture — How It Actually Works

How Does Facebook Memories Deep-Fetch a Single Photo From 15 Years Ago Out of Exabytes of Cold Storage— How It Actually Works

What Happens When a Whole Country Tries to Stream the World Cup? How Disney+ Hotstar Scaled to Handle 50+ Million Concurrent Live Viewers - How it Actually Works

Largest 31.4 TBPS DDoS Attack: How Does Cloudflare Stop the Internet from Attacks Melt Down? A Deep Dive into Cloudfare Massive Feat —How it Actually Works

2 Billion Users : How WhatsApp Scales massively to Handle Billions of Messages With Tiny Engineering Team? — How It Actually Works

Is Alexa Always Listening? How Alexa’s Processes Billions of Voice Streams in Real Time— How It Actually Works

Where Does Your Voice Go When You Say Hey Siri - How It Actually Works

What Happens in the Microsecond After You Trade? How Robinhood Routes Millions of Orders Instantly in Real time — How It Actually Works

Is Your Phone Listening? How Meta Targets Ads in Real Time — How It Actually Works

Why Do Flight Prices Change Sharply When You Refresh? How Aggregators Cache Billions of Fares Without Dead Pricing — How It Actually Works

Millions of Songs: How Spotify Decodes Your Favorite Songs and Builds Amazing Playlist in Real Time— How It Actually Works

Millions of Orders: How Uber Eats’ Makes Money and ETA for Delivery in Real Time— How It Actually Works

Billions of Views: How TikTok’s Recommendation System Makes You Super Addicted— How It Actually Works

Millions of Deliveries: How DoorDash’s Dynamic Delivery Fees Monetize Rain and Traffic and You Pay More —How It Actually Works

Massive Billions of Personalized Recommendations in Real-Time: How Instagram Scaling Actually Works

100+ Million Requests per Minute: Amazon Shopping Cart System — How It Actually Works

Trillions of Edges: How Facebook’s EdgeRank Computes Friendships Instantly — How It Actually Works

Millions of Listings: How Airbnb’s Semantic Search Understands What You Want — How It Actually Works

Millions of Dollars: How Zillow’s Zestimate Predicts Your House Price Accurately in Real Time — How It Actually Works

2 Billion+ Daily Queries: How Facebook Graph Search Maps the Social World in Real Time— How It Actually Works

Trillions of Queries: How Google’s Search & PageRank Scales Exponentially — How It Actually Works

[How to Build Tech #1] How To Actually Build End-to-End Data Pipelines ( With Implementation Code File) : How it Actually Works

[How to Build Tech #2] How To Actually Build End-to-End Machine Learning Pipelines ( With Implementation Code File) : How it Actually Works

Start System Design ( With all the case Studies) : Start here

---

What Facebook’s Notification System Actually Does

Every push notification from Facebook — “Sarah commented on your photo,” “You have 3 new friend suggestions,” “It’s been a while since you posted” — is the output of a sophisticated multi-stage ML pipeline that evaluates hundreds of features to decide:

Below is the sophisticated pipeline it uses and how it actually works—