Artwork

内容由Jay Shah提供。所有播客内容(包括剧集、图形和播客描述)均由 Jay Shah 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal
Player FM -播客应用
使用Player FM应用程序离线!

Video recommendations using Machine Learning at Facebook, News feed & Ads ranking | Amey Dharwadker

1:16:06
 
分享
 

Manage episode 365121105 series 2859018
内容由Jay Shah提供。所有播客内容(包括剧集、图形和播客描述)均由 Jay Shah 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal

Amey Dharwadker works as a Machine Learning Tech Lead Manager at Meta, supporting Facebook's Video Recommendations Ranking team and working on building and deploying personalization models for billions of users. He has also been instrumental in driving a significant increase in user engagement and revenue for the company through his work on News Feed and Ads ranking ML models. As an experienced researcher, he has co-authored publications at various AI/ML conferences and patents in the fields of recommender systems and machine learning. He has undergraduate and graduate degrees from the National Institute of Technology Tiruchirappalli (India) and Columbia University.
Time stamps of the conversation
00:00:46 Introduction
00:01:46 Getting into recommendation systems
00:05:25 Projects currently working on at Facebook, Meta
00:06:55 User satisfaction to improve recommendations
00:08:25 Implicit Metrics to improve engagement
00:11:34 Video vs product recommendations based on fixed attributes
00:13:20 Understanding video content
00:15:55 Working at Scale
00:20:02 Cold start problem
00:22:41 Data privacy concerns
00:24:36 Challenges of deploying machine learning models
00:30:56 Trade-off in metrics to boost user engagement
00:33:47 Introspecting recommender systems - Interpretability
00:37:14 Long video vs short video - how to adapt algorithms?
00:42:17 Being a Machine Learning Tech Lead Manager at Meta - work routine
00:45:00 Transitioning to leadership roles
00:50:55 Tips on interviewing for Machine Learning roles
00:57:23 Machine Learning job interviews
01:02:30 Finding your interest in AI/machine learning
01:05:24 Transitioning to ML roles within the industry
01:08:36 Remaining updated to research
01:12:00 Advice to young computer science students
More about Amey: https://research.facebook.com/people/dharwadker-amey-porobo/
Linkedin: https://www.linkedin.com/in/ameydharwadker/
Also check-out these talks on all available podcast platforms: https://jayshah.buzzsprout.com
About the Host:
Jay is a Ph.D. student at Arizona State University.
Linkedin: https://www.linkedin.com/in/shahjay22/
Twitter: https://twitter.com/jaygshah22
Homepage: https://www.public.asu.edu/~jgshah1/ for any queries.
Stay tuned for upcoming webinars!
***Disclaimer: The information contained in this video represents the views and opinions of the speaker and does not necessarily represent the views or opinions of any institution. It does not constitute an endorsement by any Institution or its affiliates of such video content.***

Checkout these Podcasts on YouTube: https://www.youtube.com/c/JayShahml
About the author: https://www.public.asu.edu/~jgshah1/

  continue reading

90集单集

Artwork
icon分享
 
Manage episode 365121105 series 2859018
内容由Jay Shah提供。所有播客内容(包括剧集、图形和播客描述)均由 Jay Shah 或其播客平台合作伙伴直接上传和提供。如果您认为有人在未经您许可的情况下使用您的受版权保护的作品,您可以按照此处概述的流程进行操作https://zh.player.fm/legal

Amey Dharwadker works as a Machine Learning Tech Lead Manager at Meta, supporting Facebook's Video Recommendations Ranking team and working on building and deploying personalization models for billions of users. He has also been instrumental in driving a significant increase in user engagement and revenue for the company through his work on News Feed and Ads ranking ML models. As an experienced researcher, he has co-authored publications at various AI/ML conferences and patents in the fields of recommender systems and machine learning. He has undergraduate and graduate degrees from the National Institute of Technology Tiruchirappalli (India) and Columbia University.
Time stamps of the conversation
00:00:46 Introduction
00:01:46 Getting into recommendation systems
00:05:25 Projects currently working on at Facebook, Meta
00:06:55 User satisfaction to improve recommendations
00:08:25 Implicit Metrics to improve engagement
00:11:34 Video vs product recommendations based on fixed attributes
00:13:20 Understanding video content
00:15:55 Working at Scale
00:20:02 Cold start problem
00:22:41 Data privacy concerns
00:24:36 Challenges of deploying machine learning models
00:30:56 Trade-off in metrics to boost user engagement
00:33:47 Introspecting recommender systems - Interpretability
00:37:14 Long video vs short video - how to adapt algorithms?
00:42:17 Being a Machine Learning Tech Lead Manager at Meta - work routine
00:45:00 Transitioning to leadership roles
00:50:55 Tips on interviewing for Machine Learning roles
00:57:23 Machine Learning job interviews
01:02:30 Finding your interest in AI/machine learning
01:05:24 Transitioning to ML roles within the industry
01:08:36 Remaining updated to research
01:12:00 Advice to young computer science students
More about Amey: https://research.facebook.com/people/dharwadker-amey-porobo/
Linkedin: https://www.linkedin.com/in/ameydharwadker/
Also check-out these talks on all available podcast platforms: https://jayshah.buzzsprout.com
About the Host:
Jay is a Ph.D. student at Arizona State University.
Linkedin: https://www.linkedin.com/in/shahjay22/
Twitter: https://twitter.com/jaygshah22
Homepage: https://www.public.asu.edu/~jgshah1/ for any queries.
Stay tuned for upcoming webinars!
***Disclaimer: The information contained in this video represents the views and opinions of the speaker and does not necessarily represent the views or opinions of any institution. It does not constitute an endorsement by any Institution or its affiliates of such video content.***

Checkout these Podcasts on YouTube: https://www.youtube.com/c/JayShahml
About the author: https://www.public.asu.edu/~jgshah1/

  continue reading

90集单集

所有剧集

×
 
Loading …

欢迎使用Player FM

Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。

 

快速参考指南