# guoday/Tencent2020_Rank1st

The code for 2020 Tencent College Algorithm Contest, and the online result ranks 1st.

Repository: https://github.com/guoday/Tencent2020_Rank1st
Canonical: https://ross.abutalabs.com/products/tencent2020_rank1st
Language: Python
License Family: other
Last push: 2023-03-16T04:19:00+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": 2233, "days_push": 1266, "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 1085, forks 319 (observed 2026-08-28T04:03:31.948228+00:00)

## What it is
The first-place winning solution code for the 2020 Tencent College Algorithm Contest, which predicts users' age and gender from 91 days of ad click history. It uses Word2Vec and BERT pretraining on click sequences with a fusion-layer classification model built in PyTorch.

## Use cases
- predict user age and gender from ad click history
- learn how to win a machine learning competition
- pretrain BERT on behavioral click sequences
- apply word2vec embeddings to user behavior data
- study a top-ranked deep learning competition solution
- build a user demographic prediction model

## When to choose
- you want a reference implementation for demographic prediction from click logs
- you are studying winning approaches for sequence-based ML competitions
- you need an example of domain-adaptive BERT pretraining on behavioral data

## When to avoid
- you need a production-ready or maintained library
- you lack GPU resources and large memory
- you need a licensed, reusable codebase (no license is provided)

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, nlp, data-science
- domain: machine-learning, artificial-intelligence, data-science
- platform: python
- tags: kaggle-competition, bert, word2vec, user-profiling, age-gender-prediction, click-through-rate, competition-solution, advertising, linux, gpu

## Member repositories
- guoday/Tencent2020_Rank1st (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:31.948228+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 2026-08-30T06:49:48.687700+00:00, confidence not recorded.
  - readme: https://github.com/guoday/Tencent2020_Rank1st (fetched 2026-08-28T04:03:31.948228+00:00, sha 6785d5acb7a7)
- Data as of 2026-08-30T08:39:29.467469+00:00.