# wzhe06/SparrowRecSys

A Deep Learning Recommender System

Repository: https://github.com/wzhe06/SparrowRecSys
Canonical: https://ross.abutalabs.com/products/sparrowrecsys
Homepage: http://wzhe.me/SparrowRecSys/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: recommender-system, deep-learning, machine-learning
Last push: 2024-06-02T04:38:14+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2311, "days_push": 822, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2776, forks 868 (observed 2026-08-28T04:07:21.421579+00:00)

## What it is
SparrowRecSys is an open-source movie recommendation system implemented as a mixed Java/Scala/Python project combining TensorFlow, Spark, and Jetty Server. It implements classic deep learning recommendation models (Word2vec, DeepWalk, Wide&Deep, DeepFM, DIN, etc.) across offline training, nearline processing, and online serving, and serves as the companion project for a practical deep learning recommender systems course.

## Use cases
- learn how to build a deep learning recommender system end to end
- implement Wide&Deep, DeepFM, or DIN recommendation models
- practice feature engineering and model training with MovieLens data
- study offline, nearline, and online recommendation architecture
- serve trained TensorFlow recommendation models behind a web server
- explore embedding techniques like Item2vec and DeepWalk for recommendations

## When to choose
- you want a complete, runnable reference implementation of a deep learning recommender system
- you are studying recommendation system architecture from offline training to online serving
- you need working examples of classic CTR and recommendation models in TensorFlow

## When to avoid
- you need a production-grade, scalable recommender platform for real traffic
- you want a pure Python or pure Java stack without mixed-language builds
- you need a maintained library with recent releases and active bug fixes

## Facets
- artifact type: learning-resource
- maturity: stable
- function: machine-learning, deep-learning, data-science, etl, streaming, http-server
- domain: machine-learning, deep-learning, education, tutorials, data-science
- platform: python, jvm, cross-platform
- tags: recommender-system, tensorflow, spark, movielens, embedding, ctr-prediction, movie-recommendation, model-serving, docker

## Member repositories
- wzhe06/SparrowRecSys (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:21.421579+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T08:16:32.974667+00:00, confidence not recorded.
  - readme: https://github.com/wzhe06/SparrowRecSys (fetched 2026-08-28T04:07:21.421579+00:00, sha edc74640dc15)
  - homepage: http://wzhe.me/SparrowRecSys/ (fetched 2026-08-29T09:55:53.069494+00:00, sha 65ec91bedcf0)
- Data as of 2026-08-30T08:39:29.467469+00:00.