# reczoo/FuxiCTR

A configurable, tunable, and reproducible library for CTR prediction https://fuxictr.github.io

Repository: https://github.com/reczoo/FuxiCTR
Canonical: https://ross.abutalabs.com/products/fuxictr
Language: Python
License: Apache-2.0
License Family: permissive
Topics: ctr-prediction, recommender-systems, ctr, cvr, pytorch
Last push: 2026-08-26T03:51:17+00:00

## Health v2 (maintenance only)
Score: 77/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 100
- inputs: {"age_days": 1798, "days_push": 7, "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 1470, forks 236 (observed 2026-08-28T04:04:49.138548+00:00)

## What it is
FuxiCTR is an open-source Python library for click-through rate (CTR) prediction built on PyTorch and TensorFlow. It offers a configurable, tunable, and reproducible model zoo covering many published CTR models with benchmark support.

## Use cases
- train CTR prediction models on click logs
- benchmark feature interaction models for recommender systems
- run hyperparameter tuning for deep CTR models
- reproduce published CTR model results
- build a CVR prediction pipeline
- prototype new CTR model architectures

## When to choose
- you need reproducible benchmarks across many CTR models
- you want configurable preprocessing and automatic tuning for CTR tasks
- you work in online advertising or sponsored search and need a CTR model zoo

## When to avoid
- you need a full production recommender system, not a research library
- your task is general recommendation beyond CTR/CVR prediction
- you need non-PyTorch/TensorFlow framework support

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, benchmarking
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: ctr-prediction, recommender-systems, pytorch, tensorflow, model-zoo, click-through-rate, reproducible-research

## Member repositories
- reczoo/FuxiCTR (main) score 77

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:49.138548+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 2026-08-30T04:34:51.076200+00:00, confidence not recorded.
  - readme: https://github.com/reczoo/FuxiCTR (fetched 2026-08-28T04:04:49.138548+00:00, sha 022f395d9b68)
  - registry_pypi: https://pypi.org/pypi/fuxictr/json (fetched 2026-08-29T11:42:45.639762+00:00, sha a6f1991838dd)
- Data as of 2026-08-30T08:39:29.467469+00:00.