Vector Search at Scale: The Production Engineer's Guide
IVF partitions space. PQ compresses memory. Together they make 100M vector search actually possible
recommenders
How Recommendation Systems Learned to Think
Recsys Series Part 2: From collaborative filtering breakthroughs to generative AI agents that can chat about your preferences and explain their reasoning
RecSys Fundamentals: The Art and Science of Digital Matchmaking
Recsys Series Part 1: Master the three core approaches that power every modern recommendation engine
Content-Based Filtering
Item Embeddings
The 3-Stage Funnel Behind Every Modern Recommender System
Two-Tower models, vector databases, cross-encoders—and how they work together at scale
Bridging the Gap: New Datasets Push Recommender Research Toward Real-World Scale - KDnuggets
Publicly available datasets in recommender research currently shaping the field.
Improving Recommender Systems & Search in the Age of LLMs
Model architectures, data generation, training paradigms, and unified frameworks inspired by LLMs.
Recommendation Algorithms You Should Know
In this article, I'll take you through the recommendation algorithms you should know and how to implement them using Python.
How to Cultivate Taste in the Age of Algorithms
When we turn to algorithms for recommendations instead of asking friends or going down hard-won cultural rabbit holes, what do we give up?
recommenders-team/recommenders: Best Practices on Recommendation Systems
Best Practices on Recommendation Systems.
Evaluation Metrics for Recommendation Systems — An Overview
Understanding the purpose and functionality of common metrics in ML packages
HackerNews Ranking Algorithm: How would you have done it?
Here's a small thought experiment that explores an alternative approach to ranking posts on HackerNews.
Hashing in Modern Recommender Systems: A Primer
Understanding the most underrated trick in applied Machine Learning
Introduction of Four Types of Item Similarity Measures
Covers how to choose the similarity measure when item embeddings are available
The Secret Sauce of Tik-Tok’s Recommendations | Shaped Blog
Dive into the inner workings of TikTok’s awesome real-time recommendation system and learn what makes it one of the best in the field!
Building a Recommender System for Amazon Products with Python
I built a recommender system for Amazon’s electronics category
An Intuitive Explanation of Collaborative Filtering
The post introduces one of the most popular recommendation algorithms, i.e., collaborative filtering. It focuses on building an intuitive understanding of the algorithm illustrated with the help of an example.
Locations product recommendations
RTFM? How to write a manual worth reading
Patience and empathy are the basis of good documentation, much as they are the basis for being a decent person. Here's a how-to for creating better open source project docs, which can help your users and grow your community.
Multi-armed bandits for dynamic movie recommendations
Making the best recommendations to anonymous audiences
grahamjenson/list_of_recommender_systems: A List of Recommender Systems and Resources
A List of Recommender Systems and Resources.
How to build B2B recommendation engines from competitor’s alternatives
Without driving yourself crazy
Multi-Relevance Ranking Model for Similar Item Recommendation
Buyers reveal a whole range of behaviors and interests when they browse our pages, so we decided to incorporate these additional purchase intent signals into our machine learning model to improve the relevance of our recommended items.
Say Hello To Recommendation Systems
A preview into one of the most prominent data science applications
Improving Shopping Recommendations for Customers Through eBay’s Relevance C
Under the new machine learning model, buyers are recommended items that are more aligned to their shopping interests on eBay.
Introducing TorchRec, a library for modern production recommendation system
We are excited to announce TorchRec, a PyTorch domain library for Recommendation Systems. This new library provides common sparsity and parallelism primitives, enabling researchers to build state-of-the-art personalization models and deploy them in production.
Algorithm-Assisted Inventory Curation
Building the raw materials for personalization at scale
Achieving High-Quality Search and Recommendation Results with DeepNLP
Speech and natural language processing (NLP) have become the foundation for most of the AI development in the enterprise today, as textual data represents a significant portion of unstructured content.
TT-Rec: Tensor Train Compression for Deep Learning Recommendation Models
The memory capacity of embedding tables in deep learning recommendation models (DLRMs) is increasing dramatically from tens of GBs to TBs across the industry. Given the fast growth in DLRMs, novel...
Latest picks: Modern Recommender Systems
Your daily dose of data science
How to build a music recommender system.
Using Spotify’s data to generate music recommendations.
RecSys Series Part 8: The 14 Properties To Take Into Account When Evaluatin
How many different ways we can evaluate RecSys?
RecSys Series Part 7: The 3 Variants of Boltzmann Machines for Collaborativ
Physics Meets Recommendations
Why Is An Obscure B-Side Pavement's Top Song On Spotify? It's Complicated.
A couple years ago, Stephen Malkmus walked into a shop and didn’t recognize himself. He was with one of his daughters, stopping at a gluten-free bakery (“Very Portland,” Malkmus jokes) when the Pavement song “Harness Your Hopes” came on — a song he had written and recorded more…
3 ways to improve recommendations | by Yinyin Liu | XOKind | Aug, 2020 | Me
It’s time to bring together recent breakthroughs in AI to help solve information overload when you need quality recommendations the most.
Improving complementary-product recommendations
New modeling approach increases accuracy of recommendations by an average of 7%.
Stacked Auto-encoder as a Recommendation System for Movie Rating Prediction
Introduction on Stacked Auto-encoder and Technical Walk-through on Model Creation using Pytorch
RecSys Series Part 5: Neural Matrix Factorization for Collaborative Filteri
Bringing Neural Architecture into Recommendations
Comprehensive Guide on Item Based Recommendation Systems
This guide will show in detail how item based recommendation system works and how to implement it in real work environment.
Building an Incremental Recommender System: Part II
Going above and beyond state-of-the-art with confidence!
Beating the baseline recommender using Graph and NLP techniques in PyTorch
Building a strong baseline recommender using PyTorch, on a regular laptop
Recommendation System Series Part 2: The 10 Categories of Deep Recommendati
Categories of Deep Recommendation Systems
Comparing Apples, Oranges and Bananas - ssense-tech - Medium
Behind every recommender system lies a bevy of metrics.
Recommender Engine - Under The Hood - DataScienceCentral.com
Many of us are bombarded with various recommendations in our day to day life, be it on e-commerce sites or social media sites. Some of the recommendations look relevant but some create range of emotions in people, varying from confusion to anger. There are basically two types of…
Pixie: a system for recommending 3 billion items to 200 million users in
5 Types of Recommenders - DataScienceCentral.com
Summary: There are five basic styles of recommenders differentiated mostly by their core algorithms. You need to understand what’s going on inside the box in order to know if you’re truly optimizing this critical tool. In our first article, “Understanding and Selecting…
Factorization Machines for Recommendation Systems
Stay up-to-date on the latest data science and AI news in the worlds of artificial intelligence, machine learning, deep learning, implementation, and more.
https://blog.statsbot.co/recommendation-system-algorithms-ba67f39ac9a3
Exploring Recommendation Systems
While we commonly associate recommendation systems with e-commerce, their application extends to any decision-making problem which requires pairing two types of things together. To understand why recommenders don’t always work as well as we’d like them to, we set out to build…
Approximate Nearest Neighbours for Recommender Systems
This post is about evaluating a couple of different approximate nearest neighbours libraries to speed up making recommendations made by matrix factorization models. In particular, the libraries I'm looking at are Annoy, NMSLib and Faiss.