In this post, you will find Recommendation Algorithms of tech giants like Spotify, YouTube, Signal Messenger, Amazon, etc. and System Designs of companies like Uber, Twitter, Netflix, Airbnb, Dropbox, Google Docs, Zoom, etc. One more thing we want to share before we jump into the article i.e. thanks for your so much love all on our previous articles.
1. Uber System Design
Uber’s technology may look straightforward but the game starts behind the scenes when A user requests a ride from the app, and a driver arrives to take them to their destination.
Uber's infrastructure consisting of thousands of services and terabytes of data supports each and every trip on the platform.
The system was predominantly written in Python and used SQLAlchemy as the ORM-layer to the database. The actual architecture was fine for running a relatively modest number of trips in a few cities.
The company's backend is now not just designed to handle taxies, instead, it can handle taxi, food delivery, cargo and a lot more.
Read More in Detail about Uber's System Design
2. YouTube Video Recommendation Algorithm
When users are spotting the videos on YouTube, a list of recommended videos are thrown below or on the right side of your device which the user might like in a certain order.
The described model in the paper focuses on the two main objectives. A Wide & Deep model architecture was used which combines the power of a wide model linear model (memorization) alongside a deep neural network (generalizations). The Wide & Deep model will generate a prediction for each of the defined (both engagement and satisfaction) objectives.
Read More in detail about YT Recommendation Algorithm
3. Spotify Music Recommendation Algorithm by Harvard Business School
How Spotify uses Machine learning to recommend the music?
The company uses three recommendation models concurrently and other techniques. Three models as described by Harvard Business School are
CF aka Collaborative Filtering: Models that analyze your behavior and compare it to other users’ behaviors
NLP aka Natural Language Processing Models - that scan the internet and analyze text about Spotify’s catalog
Audio Analysis: Models that analyze the raw audio files
Read More in detail about Spotify Recommendation Algorithm
4. Netflix System Design
Netflix operates in two clouds: AWS and Open Connect. Both clouds must work together without error to deliver endless hours of customer-pleasing video.
Three main component that plays a major role: CDN, Backend and Client
Anything that doesn’t involve serving video is handled in AWS. Everything that happens after you hit play is handled by Open Connect. Open Connect is Netflix’s custom global content delivery network (CDN).
Read More in detail about Netflix System Design
5. TikTok's ML backed Recommendation Engine
The Archetype of TikTok’s Recommendation System Design is User-Centric Design. In a simple term, TikTok will only recommend the content you would love, from a cold start adjustment to an explicit recommendation for active users.
TikTok never reveals its core algorithm to the public or the tech community. But based on the fragmented information posted via the company, and trails discovered by geeks using the reverse engineer techniques this recommendation workflow is made.
Let's divide this workflow in various parts
Step 0: Duo-Audit system for the User Generated Content (UGC)
Step 1: Cold Start
Step 2: Metric based Weighing
Step 3: User Profile Amplifier
Step 4: Boutique Trending Pool
Other Step: Delayed Ignition
Read More in detail about TikTok's ML backed Recommendation Engine
Related Post: How Big Companies Are Using Machine Learning?
6. Airbnb System Design
How do vacation rental giants like Airbnb, Booking.com and OYO work to provide such a smooth flow, from property listing, to booking, to payments? And all without a single glitch! Watch the video to find out everything from their system design, technologies, working, etc
Video Explanation of Airbnb System Design
7. Amazon Product Recommendation Algorithm
The algorithm contains 5 different main concepts:
Multiple view – shows multiple components, all the items are displayed here
User view – shows specific information about the current user in the session
Item view – shows detailed information about the current item
Recommendation view – shows recommended items based on the current item
Data view – visualizes the data structure used by the recommendation algorithm
8.Dropbox System Design
Have you ever wonder how these services works internally to provide features like File Upload, Update, Delete and Download?
File versioning
File and folder sync
Here is the high-level explanation of how these systems works under the hood
Video Explanation of Dropbox System Design
Check out other 11 System Designs and Recommendation Algorithms from here: System Designs and Recommendation Algorithms of Stock Exchange, Google Docs, Yelp, Cricbuzz, Zoom, Signal Messenger, BookMyShow, etc
Top comments (0)