Recommenders

Visit Tool

Recommenders is an Open Source tool that provides best practices and examples for building recommendation systems. It assists researchers and developers in prototyping, experimenting with, and operationalizing various recommendation algorithms.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is recommenders?

Recommenders is an open-source project under the Linux Foundation of AI and Data, offering a comprehensive toolkit for building and evaluating recommendation systems. It provides examples and best practices through Jupyter notebooks, covering data preparation, model building with classical and deep learning algorithms (like ALS, xDeepFM, and LightGCN), evaluation with offline metrics, model selection, optimization, and operationalization on Azure. The repository includes implementations of numerous state-of-the-art algorithms, utilities for common tasks like dataset loading and data splitting, and detailed documentation to support researchers, developers, and enthusiasts in their recommendation system endeavors.

Best used for

Ideal for data scientists, machine learning engineers, and researchers who need to develop, evaluate, and deploy recommendation systems. Especially valuable for those looking for a comprehensive collection of algorithms and best practices, from data preparation to production operationalization.

Common actions

build recommendation systems

evaluate recommendation models

prototype AI algorithms

optimize machine learning models

low-code/no-codeopen-sourceworkflowsdeepfakeautomated workflow"AI Agents"collaborationgithub copilotface swapping

Capabilities

Key features

Data preparation utilities
Classical recommendation algorithms
Deep learning recommendation algorithms
Offline metric evaluation
Model optimization tools
Production operationalization examples
Jupyter notebook examples

Target Audience

data scientistsmachine learning engineersresearchersdevelopers

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What types of recommendation algorithms are included in Recommenders?

Recommenders includes a wide range of algorithms, covering both collaborative filtering (e.g., ALS, LightGCN, SASRec) and content-based filtering (e.g., DKN, LightGBM, Vowpal Wabbit). It features both classical and deep learning approaches, with examples provided in Jupyter notebooks.

What environments does Recommenders support for running models?

The algorithms in Recommenders support various environments including CPU, GPU, and PySpark. Specific algorithms may be optimized for certain environments, and the documentation provides details on setup and configuration for different platforms like Linux, Windows, and macOS.

How can I get started with using the Recommenders project?

To get started, you can install the core recommenders package using `uv pip install recommenders` and then clone the GitHub repository. The project provides example Jupyter notebooks, such as `sar_movielens.ipynb`, which can be run in VS Code with a dedicated Jupyter kernel.

Trending

Subcategories trending in E-commerce

Storefront & Website Inventory & Supply Chain Marketplace Tools Product Descriptions Pricing & Revenue Product Photography

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce