Applied ML | Recommender systems

Home
Notes
Archive
About
Two tower models for retrieval of recommendations
Fourth post in this series on personalized recommendations
 • 
Gaurav Chakravorty
1
Early (Stage) Ranking in recommender systems
We look at "early (stage) ranking", why it is needed, what is success for it and end with a baseline implementation of it.
 • 
Gaurav Chakravorty
3
How to build ML-first products
Problems companies face in adopting ML and how to solve them
 • 
Gaurav Chakravorty
Ranking model calibration in recommender systems
We define calibration of ranking models in calibration, the benefit it can bring to prioritize calibration and how to achieve it without affecting…
 • 
Gaurav Chakravorty
 and 
Marc Ferradou
2
Recommendations using graph neural networks
personalized recommendations #8
 • 
Gaurav Chakravorty
4
Personalized short-video recommender systems
To recap the previous two articles in this short-video recommendation series, part-1 "Using online learning in short-video recommendations” showed a…
 • 
Gaurav Chakravorty
Friend Recommendation Retrieval in a social network
From Graph Search to Deep Neural Two-Tower Models
 • 
Gaurav Chakravorty
, 
Parag Agrawal
, and 
Andrew Dodd
User representation in a recommender system | memorization vs generalization
We look at memorization, generalization and mixture of representations based implementations for user preference representation in a recommender system
 • 
Gaurav Chakravorty
, 
Hong Chen
, and 
Saurabh Gupta
Scalable Embedding based retrieval for target side value
Addressing Scalability Challenges in Two-Sided Embedding based Recommendations
 • 
Gaurav Chakravorty
 and 
Ridwan Amure
Reducing selection bias / popularity bias in ranking
Through the post, code and videos we show how to make your multi-task ranking model unbiased
 • 
Gaurav Chakravorty
 and 
Ameya Raul
How to implement Generative Retrieval
GenAI meets recommender systems
 • 
Gaurav Chakravorty
 and 
Samson Komo
4
1:18:39
Fairness in ranking
Helping Elon build a "fair" ranking algorithm
 • 
Gaurav Chakravorty
© 2025 RecSysML Journal team
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture