kang205/SASRec

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1007 stars · 194 forks observed · 2026-10-19

What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-07, confidence 0.95

Official TensorFlow implementation of SASRec (Self-Attentive Sequential Recommendation), a Transformer-based sequential recommendation model from an ICDM'18 paper. It includes training scripts, preprocessing utilities, and preprocessed benchmark datasets such as Amazon reviews, Steam, and MovieLens-1M.

Use cases

• train a self-attentive sequential recommendation model
• reproduce SASRec paper results on ml-1m
• build a next-item recommendation model from user interaction logs
• benchmark against RNN and CNN sequential recommenders
• preprocess Amazon review data for recommendation experiments
• use the Steam reviews dataset for recommender research

When to choose

• you need the canonical reference implementation of SASRec for research or comparison
• you want a proven Transformer-based sequential recommender with included benchmark datasets
• your stack already uses TensorFlow 1.x and Python 2

When to avoid

• you need a modern maintainable stack - it depends on TensorFlow 1.12 and Python 2
• you prefer PyTorch, in which case the community pmixer/SASRec.pytorch port is better
• you want a production-ready recommendation service rather than research code

Facets

library · maturity maintenance

machine-learning deep-learning search-engine machine-learning data-science python recommender-system self-attention tensorflow sequential-recommendation transformer icdm-2018 research-code datasets recommender-systems linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="kang205/SASRec")