# Doragd/Algorithm-Practice-in-Industry

搜索、推荐、广告、用增等工业界实践文章收集（来源：知乎、Datafuntalk、技术公众号）

Repository: https://github.com/Doragd/Algorithm-Practice-in-Industry
Canonical: https://ross.abutalabs.com/products/algorithm-practice-in-industry
Language: HTML
License: BSD-2-Clause
License Family: permissive
Last push: 2026-08-26T04:16:20+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 99, release rhythm 35, longevity 93
- inputs: {"age_days": 1311, "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 4574, forks 488 (observed 2026-08-28T04:08:53.642297+00:00)

## What it is
A curated collection of industry practice articles, top-conference papers, and blog posts on search, recommendation, and advertising (搜广推) algorithms, plus an automated paper bot. It uses GitHub Actions to fetch daily arXiv papers, rank/translate them with LLMs, generate web pages, and push updates to Feishu groups.

## Use cases
- find industry articles on recommendation and search algorithms
- get daily arXiv paper recommendations for information retrieval
- track top-conference papers in RecSys, SIGIR, KDD
- set up a Feishu bot that pushes new ML papers daily
- learn how search, ads, and recommendation systems work in practice

## When to choose
- you work in search, recommendation, or advertising and want curated learning material
- you want an automated arXiv digest with LLM-based ranking and translation
- you need a maintained list of top-conference papers in the 搜广推 space

## When to avoid
- you need a production recommendation engine or library code
- you want a general-purpose paper tracker outside search/ads/recommendation
- you don't read Chinese, since most curated content is in Chinese

## Facets
- artifact type: learning-resource
- maturity: active
- function: web-scraping, nlp, machine-learning, workflow-automation, data-visualization
- domain: machine-learning, tutorials
- platform: python, cli
- tags: recommendation-systems, computational-advertising, arxiv-papers, feishu-bot, curated-list, github-actions, search-engine, natural-language-processing, search, automation, web-server

## Member repositories
- Doragd/Algorithm-Practice-in-Industry (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:53.642297+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 2026-08-29T18:19:56.547790+00:00, confidence not recorded.
  - readme: https://github.com/Doragd/Algorithm-Practice-in-Industry (fetched 2026-08-28T04:08:53.642297+00:00, sha 3369e66e73f0)
- Data as of 2026-08-30T08:39:29.467469+00:00.