# wepe/O2O-Coupon-Usage-Forecast

1st Place Solution for O2O Coupon Usage Forecast

Repository: https://github.com/wepe/O2O-Coupon-Usage-Forecast
Canonical: https://ross.abutalabs.com/products/o2o-coupon-usage-forecast
Language: Python
License Family: other
Last push: 2018-03-08T06:06:45+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": 3537, "days_push": 3100, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1419, forks 835 (observed 2026-08-28T04:04:40.470826+00:00)

## What it is
The 1st place winning solution code for the Alibaba Tianchi O2O Coupon Usage Forecast competition, written in Python. It provides feature engineering pipelines and XGBoost/GBDT/RandomForest model ensembling for predicting whether users will redeem coupons within 15 days.

## Use cases
- predict whether users will redeem coupons after claiming them
- learn feature engineering techniques for tabular competition data
- study a winning machine learning competition solution
- build a coupon redemption prediction model with xgboost
- learn how to ensemble gradient boosting models
- understand data leakage exploitation in competition settings

## When to choose
- you want to study a top-ranked competition solution for tabular prediction
- you need reference feature engineering ideas for user-merchant interaction data
- you are learning XGBoost and model ensembling on real-world e-commerce data

## When to avoid
- you need production-ready, maintained software with a license
- you want a general-purpose coupon marketing tool rather than competition code
- you need features that are valid in real business settings, since some exploit competition leakage

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, data-science
- domain: machine-learning, data-science, e-commerce
- platform: python
- tags: kaggle-competition, xgboost, feature-engineering, coupon-redemption, tianchi, gradient-boosting, recommender-systems

## Member repositories
- wepe/O2O-Coupon-Usage-Forecast (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.470826+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 2026-08-30T04:37:54.642571+00:00, confidence not recorded.
  - readme: https://github.com/wepe/O2O-Coupon-Usage-Forecast (fetched 2026-08-28T04:04:40.470826+00:00, sha 6331153ab02a)
- Data as of 2026-08-30T08:39:29.467469+00:00.