# ycjuan/kaggle-2014-criteo

Repository: https://github.com/ycjuan/kaggle-2014-criteo
Canonical: https://ross.abutalabs.com/products/kaggle-2014-criteo
Language: C++
License: NOASSERTION
License Family: other
Archived: true
Last push: 2024-08-16T04:31:37+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4347, "days_push": 747, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1254, forks 607 (observed 2026-08-28T04:04:08.768574+00:00)

## What it is
The winning '3 Idiots' solution code for the 2014 Kaggle Criteo Display Advertising Challenge, built around field-aware factorization machines (FFM). It includes C++ executables and Python scripts for converting, preparing, and running predictions on the Criteo dataset.

## Use cases
- reproduce the winning solution for the Kaggle Criteo display advertising challenge
- train field-aware factorization machine models on CTR prediction data
- convert the released Criteo text dataset to competition csv format
- learn how top Kaggle teams approached large-scale click-through-rate prediction
- run FFM-based experiments on large advertising datasets

## When to choose
- you want to replicate or study the winning 2014 Criteo competition approach
- you need a proven FFM pipeline for click-through-rate prediction
- you have the required 40GB+ memory Unix environment and the Criteo dataset

## When to avoid
- you need a modern, maintained CTR prediction library with active support
- you work on Windows or lack 40GB+ RAM and 100GB disk space
- you want a general-purpose machine learning framework rather than a competition-specific solution

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, data-science, etl
- domain: machine-learning, data-science
- platform: cpp, python
- tags: kaggle, criteo, factorization-machines, ffm, click-through-rate, display-advertising, competition-solution, algorithms, linux

## Member repositories
- ycjuan/kaggle-2014-criteo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:08.768574+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 2026-08-30T05:07:26.611908+00:00, confidence not recorded.
  - readme: https://github.com/ycjuan/kaggle-2014-criteo (fetched 2026-08-28T04:04:08.768574+00:00, sha c6bce088762f)
- Data as of 2026-08-30T08:39:29.467469+00:00.