# tangxyw/RecSysPapers

推荐/广告/搜索领域工业界经典以及最前沿论文集合。A collection of industry classics and cutting-edge papers in the field of recommendation/advertising/search.

Repository: https://github.com/tangxyw/RecSysPapers
Canonical: https://ross.abutalabs.com/products/recsyspapers
Homepage: https://tangxyw.github.io/
Language: Python
License: BSD-2-Clause
License Family: permissive
Topics: calibration, causal-inference, cold-start, contrastive-learning, debias, distillation, diverse, fairness, match, papers, rank, re-rank, recommendation-system, feedback-delay, pre-rank, look-alike, multi-scenario, multi-task, reinforcement-learning, multi-modal
Last push: 2026-06-11T00:57:36+00:00

## Health v2 (maintenance only)
Score: 71/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 86, release rhythm 35, longevity 100
- inputs: {"age_days": 1478, "days_push": 84, "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 2189, forks 265 (observed 2026-08-28T04:06:23.956366+00:00)

## What it is
A curated collection of 948+ industry and academic papers on recommendation systems, advertising, and search, organized by topics such as ranking, matching, multi-task learning, debiasing, and calibration. It is continuously updated and serves as a study and reference resource for practitioners and researchers.

## Use cases
- find classic papers on recommendation systems
- study CTR prediction and ranking models
- learn about multi-task and multi-scenario modeling
- research debiasing and calibration techniques in recsys
- keep up with cutting-edge industrial recsys papers
- prepare for machine learning interviews in ads or search

## When to choose
- you need a comprehensive, categorized reading list for recommendation/advertising/search research
- you want to track industry classics and frontier papers in one place

## When to avoid
- you need runnable code implementations rather than papers
- you need papers outside recommendation, advertising, or search domains

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, search-engine, developer-tools
- domain: machine-learning, artificial-intelligence, tutorials, awesome-lists
- platform: cross-platform
- tags: recommendation-systems, papers, advertising, search, ctr-prediction, reading-list, curated-collection

## Member repositories
- tangxyw/RecSysPapers (main) score 71

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:23.956366+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 2026-08-30T02:47:44.957445+00:00, confidence not recorded.
  - readme: https://github.com/tangxyw/RecSysPapers (fetched 2026-08-28T04:06:23.956366+00:00, sha 829ca308a1a5)
  - homepage: https://tangxyw.github.io/ (fetched 2026-08-29T10:28:05.766939+00:00, sha 87562e8c1587)
- Data as of 2026-08-30T08:39:29.467469+00:00.