ad-ranking-recsys-collection

A collection of popular articles and papers on Ad ranking recommender systems

Industry Implementations:

Twitter:

• Ad Candidate Ranking https://blog.twitter.com/engineering/en_us/topics/infrastructure/2019/splitnet-architecture-for-ad-candidate-ranking

Snapchat:

• Ad Ranking https://eng.snap.com/machine-learning-snap-ad-ranking

Tencent:

• Tencent using NVIDIA Merlin: https://medium.com/nvidia-merlin/leading-design-and-development-of-the-advertising-recommender-system-at-tencent-an-interview-with-37f1eed898a7

• Tencent using NVIDIA Merlin HugeCTR: https://www.nvidia.com/en-us/on-demand/session/gtcspring21-s31820/?ncid=so-medi-863304

Pinterest:

• Multi tower models and AutoML https://medium.com/pinterest-engineering/how-we-use-automl-multi-task-learning-and-multi-tower-models-for-pinterest-ads-db966c3dc99e
• Calbiration Utility https://medium.com/pinterest-engineering/multi-task-learning-and-calibration-for-utility-based-home-feed-ranking-64087a7bcbad
• Contextual Relevance https://medium.com/pinterest-engineering/contextual-relevance-in-ads-ranking-63c2ff215aa2

Swiggy:

• Contextual Bandits for Ads RecSys https://bytes.swiggy.com/contextual-bandits-for-ads-recommendations-ec210775fcf

OLX:

• Ad Ranking https://tech.olx.com/ranking-ads-with-machine-learning-ee03d7734bf4

Calibration in General:

• Scale Calibration of Deep Ranking Models - Google Research https://storage.googleapis.com/pub-tools-public-publication-data/pdf/149935a08dc9db00fd92d0679061df7d79e601fc.pdf

Literature Survey:

• Click-Through Rate Prediction in Online Advertising: A Literature Review Yanwu Yang, Panyu Zhai : https://arxiv.org/abs/2202.10462