zhougr1993/DeepInterestNetwork

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1733 stars · 554 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A TensorFlow demo implementation of the Deep Interest Network (DIN) paper for click-through rate prediction, run on the Amazon electronics dataset. It also includes baseline competitor models (Wide&Deep, PNN, DeepFM), though the authors recommend their newer DIEN implementation instead.

Use cases

• reproduce DIN paper results on Amazon data
• implement click-through rate prediction with deep learning
• compare DIN against PNN, DeepFM, and Wide&Deep baselines
• learn how attention-based user interest modeling works
• benchmark CTR models with GAUC metrics

When to choose

• you need a reference implementation of the DIN paper
• you want to experiment with attention mechanisms for CTR prediction
• you need baseline CTR models for comparison on the Amazon dataset

When to avoid

• you want production-quality code - the authors state the code quality is poor
• you want the latest results - use the DIEN implementation instead
• you lack a GPU with at least 10GB memory
• you need a maintained library - last release was 2020 and it targets old TensorFlow versions

Facets

library · maturity maintenance

machine-learning deep-learning machine-learning deep-learning python ctr-prediction recommendation tensorflow deep-interest-network research-code amazon-dataset algorithms

Member repositories

For agents

markdown · JSON · MCP: product_card(name="zhougr1993/DeepInterestNetwork")