Скачать с ютуб Evolution of Pinterest's Ranking System: From GBDT to Deep Learning Models | Recommendation System в хорошем качестве

Evolution of Pinterest's Ranking System: From GBDT to Deep Learning Models | Recommendation System

#machinelearning #datascience #artificialgeneralintelligence #artificialintelligence #datatrek #recsys #recommendations #pinterest #llm #medium #analytics #statistics Blog Link:   / evolution-of-ads-conversion-optimization-m...   Other Recsys Videos on the Channel: Netflix's Calibrated Recommendations    • Tailored Streaming: Understanding Net...   Netflix's Unified Recommendation ML Model:    • Netflix's Unified ML Model: Deep Dive...   Evolution of Recommendation Systems | Instagram Pinterest Twitter    • Evolution of Recommendation Systems |...   Multi-Armed Bandit Startegies:    • Multi-Armed Bandit Strategies: Epsilo...   Overcoming Biases for a Better Recommender System | How Tech-Titans Combat Recommender System Biases    • Overcoming Biases for a Better Recomm...   Building Scalable Query-Item Two-Tower Model based Retrieval System    • Building Scalable Retrieval System wi...   Chapters 0:00 - 0:43 Video Intro 0:44 - 1:51 Modern-Day Scalable Recommendation System 1:52 - 3:27 Evolution of Ranking System @ Pinterest 3:28 - 5:30 GBDT-based Ranking Model 5:31 - 8:41 Why Deep learning-based models Outperform Tree-based models? 8:42 - 11:05 Wide & Deep Network 11:06 - 13:57 DeepFM-based Network 13:58-15:51 Deep & Cross Network 15:52-17:16 Transformer-based Network 17:17 - 20:27 MaskNet-based Network 20:28 - 23:02 Modern-Day Multi-task based learning, Ensemble & User-Sequence Modeling Architecture 23:03 - 23:27 Conclusion With the increase in the scale of data and new research around ML techniques being published every day, the ranking layer in recommendation systems at Pinterest has evolved accordingly. It started with tree-based GBDT models and transitioned through various deep learning architectures like Wide & Deep Network, DeepFM, Deep & Cross Network, Transformer, and MaskNet, to the current-day architecture utilizing the strengths of multi-task learning, ensemble techniques, and user-sequence modeling. We will cover all these architectures and see how one led to another. We will also explore why deep learning-based models have outperformed tree-based models for ranking tasks in recommendation systems. Check out the latest video covering the entire evolution of the ranking system at Pinterest. Connect with Me Linkedin:   / mungoliabhishek81   Topmate: https://topmate.io/mungoli_abhishek Instagram:   / simplyspartanx   Twitter:   / mungoliabhishek   LinkedIn DataTrek:   / datatrek-channel   LinkTree: https://linktr.ee/abhishekmungoli #datascience #machinelearning #statistics #deeplearning #programming #python #datatrek #youtube #interview #interviewpreparation #interviewquestions #datascientist #dataanalytics #machinelearningengineer #datasciencejobs #datasciencetraining #datasciencecourse #datascienceenthusiast #career #careeropportunities #careergrowth #careerdevelopment #datascienceenthusiast #interviewing #ml #ai #datatrek #datascience #machinelearning #statistics #deeplearning #ai About DataTrek Series    • Introduction to DataTrek: Data Scienc...   Business Enquiries: [email protected] Find me on Instagram: www.instagram.com/simplyspartanx/ Music: www.bensound.com/royalty-free-music