otto-de/TRON
⚡️ Implementation of TRON: Transformer Recommender using Optimized Negative-sampling, accepted at ACM RecSys 2023.
TRON helps e-commerce and content platforms improve their product recommendations for individual users based on their current browsing session. You provide historical user interaction data (like clicks or views within a session), and TRON outputs highly relevant, personalized recommendations. This is ideal for product managers, merchandisers, or data scientists working to enhance user experience and drive engagement on online platforms.
No commits in the last 6 months.
Use this if you need to generate fast, accurate, and scalable product or content recommendations based on real-time user session activity.
Not ideal if your recommendation needs are not session-based, or if you prefer simpler models that don't require advanced configuration for negative sampling and loss functions.
Stars
74
Forks
4
Language
Python
License
MIT
Category
Last pushed
May 28, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/otto-de/TRON"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sb-ai-lab/RePlay
A Comprehensive Framework for Building End-to-End Recommendation Systems with State-of-the-Art Models
MalihehIzadi/SoftwareTagRecommender
A tag recommender based on SOTA machine learning algorithms to automatically recommending tags...
deepmancer/advanced-recommender-system
Advance information retrieval system that combines advanced indexing, machine learning, and...
januverma/transformers-for-sequential-recommendation
Notebooks on using transformers for sequential recommendation tasks
leuas/Vrdndi
A full-stack context-aware productivity-focused recommendation system