際際滷shows by User: RoelofVanZwol / http://www.slideshare.net/images/logo.gif 際際滷shows by User: RoelofVanZwol / Thu, 10 Sep 2020 21:11:30 GMT 際際滷Share feed for 際際滷shows by User: RoelofVanZwol Marketplace in motion - AdKDD keynote - 2020 /slideshow/marketplace-in-motion-adkdd-keynote-2020/238445455 roelofvanzwol-marketplaceinmotion-adkdd2020-200910211130
It this AdKDD keynote presentation, Roelof van Zwol gives a high level overview of the Marketplace design principles at Pinterest with a strong focus on Putting Pinners first by highlighting how ad relevance is used to improve the quality of Ads shown to users. Moreover he will review various ML techniques underlying the Ads delivery funnel and detail how over the past 2 years the Ads retrieval and ranking algorithms have evolved in the current state of the art.]]>
It this AdKDD keynote presentation, Roelof van Zwol gives a high level overview of the Marketplace design principles at Pinterest with a strong focus on Putting Pinners first by highlighting how ad relevance is used to improve the quality of Ads shown to users. Moreover he will review various ML techniques underlying the Ads delivery funnel and detail how over the past 2 years the Ads retrieval and ranking algorithms have evolved in the current state of the art.]]> Thu, 10 Sep 2020 21:11:30 GMT /slideshow/marketplace-in-motion-adkdd-keynote-2020/238445455 RoelofVanZwol@slideshare.net(RoelofVanZwol) Marketplace in motion - AdKDD keynote - 2020 RoelofVanZwol It this AdKDD keynote presentation, Roelof van Zwol gives a high level overview of the Marketplace design principles at Pinterest with a strong focus on Putting Pinners first by highlighting how ad relevance is used to improve the quality of Ads shown to users. Moreover he will review various ML techniques underlying the Ads delivery funnel and detail how over the past 2 years the Ads retrieval and ranking algorithms have evolved in the current state of the art. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/roelofvanzwol-marketplaceinmotion-adkdd2020-200910211130-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> It this AdKDD keynote presentation, Roelof van Zwol gives a high level overview of the Marketplace design principles at Pinterest with a strong focus on Putting Pinners first by highlighting how ad relevance is used to improve the quality of Ads shown to users. Moreover he will review various ML techniques underlying the Ads delivery funnel and detail how over the past 2 years the Ads retrieval and ranking algorithms have evolved in the current state of the art.
Marketplace in motion - AdKDD keynote - 2020 from Roelof van Zwol
]]> 2374 0 https://cdn.slidesharecdn.com/ss_thumbnails/roelofvanzwol-marketplaceinmotion-adkdd2020-200910211130-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Correlation, causation and incrementally recommendation problems at netflix september 2018 - university of antwerp /slideshow/correlation-causation-and-incrementally-recommendation-problems-at-netflix-september-2018-university-of-antwerp/115464815 correlationcausationandincrementallyrecommendationproblemsatnetflix-september2018-universityofantwer-180919185200
Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During this presentation I will cover some of the personalization and recommendation tasks that jointly define the Netflix user experience that entertains more that 130M members world wide. In particular, I will focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as causality, incrementality and explore-exploit strategies. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences.]]>
Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During this presentation I will cover some of the personalization and recommendation tasks that jointly define the Netflix user experience that entertains more that 130M members world wide. In particular, I will focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as causality, incrementality and explore-exploit strategies. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences.]]> Wed, 19 Sep 2018 18:52:00 GMT /slideshow/correlation-causation-and-incrementally-recommendation-problems-at-netflix-september-2018-university-of-antwerp/115464815 RoelofVanZwol@slideshare.net(RoelofVanZwol) Correlation, causation and incrementally recommendation problems at netflix september 2018 - university of antwerp RoelofVanZwol Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During this presentation I will cover some of the personalization and recommendation tasks that jointly define the Netflix user experience that entertains more that 130M members world wide. In particular, I will focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as causality, incrementality and explore-exploit strategies. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/correlationcausationandincrementallyrecommendationproblemsatnetflix-september2018-universityofantwer-180919185200-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During this presentation I will cover some of the personalization and recommendation tasks that jointly define the Netflix user experience that entertains more that 130M members world wide. In particular, I will focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as causality, incrementality and explore-exploit strategies. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences.
Correlation, causation and incrementally recommendation problems at netflix september 2018 - university of antwerp from Roelof van Zwol
]]> 899 3 https://cdn.slidesharecdn.com/ss_thumbnails/correlationcausationandincrementallyrecommendationproblemsatnetflix-september2018-universityofantwer-180919185200-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Sprezzatura - Roelof van Zwol - May 2018 /slideshow/sprezzatura-roelof-van-zwol-may-2018/96565418 sprezzatura-roelofvanzwol-may2018-180509214049
Sprez.za.tura: "It is an art which does not seem to be an art". Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During the presentation, we focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as correlation, causation, incrementality and multi-armed bandits. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences.]]>
Sprez.za.tura: "It is an art which does not seem to be an art". Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During the presentation, we focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as correlation, causation, incrementality and multi-armed bandits. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences.]]> Wed, 09 May 2018 21:40:49 GMT /slideshow/sprezzatura-roelof-van-zwol-may-2018/96565418 RoelofVanZwol@slideshare.net(RoelofVanZwol) Sprezzatura - Roelof van Zwol - May 2018 RoelofVanZwol Sprez.za.tura: "It is an art which does not seem to be an art". Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During the presentation, we focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as correlation, causation, incrementality and multi-armed bandits. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/sprezzatura-roelofvanzwol-may2018-180509214049-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> Sprez.za.tura: &quot;It is an art which does not seem to be an art&quot;. Within Netflix, personalization is a key differentiator, helping members to quickly discover new content that matches their taste. Done well, it creates an immersive user experience, however when the recommendation is out of tune, it is immediately noticed by our members. During the presentation, we focus on several of the algorithmic challenges related to the launch of new Netflix originals in the service, and go over concepts such as correlation, causation, incrementality and multi-armed bandits. The research presented in this talk represents the collaborative efforts of a team of research scientists and engineers at Netflix on our journey to create best in class user experiences.
Sprezzatura - Roelof van Zwol - May 2018 from Roelof van Zwol
]]> 1222 1 https://cdn.slidesharecdn.com/ss_thumbnails/sprezzatura-roelofvanzwol-may2018-180509214049-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 Interactive Recommender Systems /slideshow/interactive-recommender-systems/52867998 interactiverstutorial-recsys-2015-150916221009-lva1-app6891
by Harald Steck (Netflix Inc., US), Roelof van Zwol (Netflix Inc., US) and Chris Johnson (Spotify Inc., US) 際際滷s of the tutorial on interactive recommender systems at the 2015 conference on Recommender Systems (RecSys). Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction. In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests. The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems. DATE: Wednesday, Sept 16, 2015, 11:00-12:30]]>
by Harald Steck (Netflix Inc., US), Roelof van Zwol (Netflix Inc., US) and Chris Johnson (Spotify Inc., US) 際際滷s of the tutorial on interactive recommender systems at the 2015 conference on Recommender Systems (RecSys). Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction. In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests. The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems. DATE: Wednesday, Sept 16, 2015, 11:00-12:30]]> Wed, 16 Sep 2015 22:10:09 GMT /slideshow/interactive-recommender-systems/52867998 RoelofVanZwol@slideshare.net(RoelofVanZwol) Interactive Recommender Systems RoelofVanZwol by Harald Steck (Netflix Inc., US), Roelof van Zwol (Netflix Inc., US) and Chris Johnson (Spotify Inc., US) 際際滷s of the tutorial on interactive recommender systems at the 2015 conference on Recommender Systems (RecSys). Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction. In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests. The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems. DATE: Wednesday, Sept 16, 2015, 11:00-12:30 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/interactiverstutorial-recsys-2015-150916221009-lva1-app6891-thumbnail.jpg?width=120&amp;height=120&amp;fit=bounds" /><br> by Harald Steck (Netflix Inc., US), Roelof van Zwol (Netflix Inc., US) and Chris Johnson (Spotify Inc., US) 際際滷s of the tutorial on interactive recommender systems at the 2015 conference on Recommender Systems (RecSys). Interactive recommender systems enable the user to steer the received recommendations in the desired direction through explicit interaction with the system. In the larger ecosystem of recommender systems used on a website, it is positioned between a lean-back recommendation experience and an active search for a specific piece of content. Besides this aspect, we will discuss several parts that are especially important for interactive recommender systems, including the following: design of the user interface and its tight integration with the algorithm in the back-end; computational efficiency of the recommender algorithm; as well as choosing the right balance between exploiting the feedback from the user as to provide relevant recommendations, and enabling the user to explore the catalog and steer the recommendations in the desired direction. In particular, we will explore the field of interactive video and music recommendations and their application at Netflix and Spotify. We outline some of the user-experiences built, and discuss the approaches followed to tackle the various aspects of interactive recommendations. We present our insights from user studies and A/B tests. The tutorial targets researchers and practitioners in the field of recommender systems, and will give the participants a unique opportunity to learn about the various aspects of interactive recommender systems in the video and music domain. The tutorial assumes familiarity with the common methods of recommender systems. DATE: Wednesday, Sept 16, 2015, 11:00-12:30
Interactive Recommender Systems from Roelof van Zwol
]]> 3063 4 https://cdn.slidesharecdn.com/ss_thumbnails/interactiverstutorial-recsys-2015-150916221009-lva1-app6891-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post http://activitystrea.ms/schema/1.0/posted 0 https://cdn.slidesharecdn.com/profile-photo-RoelofVanZwol-48x48.jpg?cb=1623613368 www.linkedin.com/in/roelofvanzwol/ https://cdn.slidesharecdn.com/ss_thumbnails/roelofvanzwol-marketplaceinmotion-adkdd2020-200910211130-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/marketplace-in-motion-adkdd-keynote-2020/238445455 Marketplace in motion ... https://cdn.slidesharecdn.com/ss_thumbnails/correlationcausationandincrementallyrecommendationproblemsatnetflix-september2018-universityofantwer-180919185200-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/correlation-causation-and-incrementally-recommendation-problems-at-netflix-september-2018-university-of-antwerp/115464815 Correlation, causation... https://cdn.slidesharecdn.com/ss_thumbnails/sprezzatura-roelofvanzwol-may2018-180509214049-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/sprezzatura-roelof-van-zwol-may-2018/96565418 Sprezzatura - Roelof ...