Events Add an event Speakers Talks Collections
 
MLconf Online 2020
November 6, 2020, Online
MLconf Online 2020
Request Q&A
MLconf Online 2020
From the conference
MLconf Online 2020
Request Q&A
Video
Shopping Recommendations at Pinterest
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Add to favorites
238
I like 0
I dislike 0
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
  • Description
  • Transcript
  • Discussion

About the talk

Shopping is at the core of Pinterest’s mission to help people create a life they love. Every day hundreds of millions of users come to Pinterest to find inspiration to decorate their home, to wear outfits on different occasions, host parties and various other things to create a better life. Shopping recommendation connects those inspiration content to actual products that users can buy and create a better life for themselves. Pinterest provides shopping recommendations across different surfaces, on closeup of a pin, on users' boards, on search results etc.

In this talk, I'll provide under the hood details of Shopping recommendations at Pinterest. Shopping recommenders at Pinterest are some of the most large scale recommender systems in the world. They provide most relevant and visually similar recommendations leveraging the giant pin-board graph, visual similarity, user profile and many other features. A multi-head deep neural network is used to score and select the most relevant recommendations in real-time from hundreds of millions of products. Then multiple different types of Shopping recommendation modules are put together using a multi-armed bandit framework. The audience can expect to gain a deeper understanding of how a large scale recommendation system works, how deep learning and graph convolutional network is used to determine product similarity and how multi-armed bandit is used to put together different shopping recommendation modules.

About speaker

Somnath Banerjee
Head of Shopping Discovery at Pinterest

Somnath Banerjee is the head of shopping discovery at Pinterest. He and the team is responsible for developing the most personalized, visual and inspirational Shopping experience for the users. The team applies cutting edge machine learning and deep learning techniques in recommendation, search and whole page optimization. Previously, Somnath was a director of machine learning and the head of search quality for Walmart.com. Somnath has decades of experience in working on machine learning and leading machine learning teams at various organizations. He holds a PhD in Information Retrieval and has published a number of papers in prestigious conferences like SIGIR, WWW etc. Somnath has been an invited speaker on E-commerce and machine learning at conferences world-wide; IDG at Seoul and AI Summit at San Francisco, Nvidia GTC at San Jose etc.

View the profile
Share

Play everyone, welcome to this wonderful conference and welcome to my Jog and chopping the donation. I'm Sonia Banerjee of the shopping Discovery, Team adventure. Glenn's on how we do that. The currently Global annual income of retail sales is four trillion. Dollars comes from outside invasions generated by driving. In this talk, I'll discuss how to sharpen your combination practice. The dog is divided into three section. Boston will introduce you to our shopping Adventure.

Do our shopping. Let's see how we can collect and organize them into boards. We use the term to refer to email a video of Tori saved on the boat to travel home. Interesting fact, about we showed 40% of our users. Can you find Thank you, five times, higher than other social media, like, Facebook, Snapchat, and all. Let's see how our product, this is what we call the shipping information, xcetera. Honda Princeton rehab. Examples of ways we are Home Depot Home Depot. But Pinterest shopping

from the journey from inspiration to pass gas. You look stupid going to start with a broad idea, like set up living room light. How much longer? Charming up, interesting, ideas on Pinterest? Drive me to do Friends shopping. When Janet gas into living room, c a living room. 1 stocks into one of those, like the Florida line. What she wants. Apart from these countries has some. We also have things are better, but the user can choose. Future star great, London. I think we have 152 million monthly active users across the globe this year.

How long is today live in us and UK? Hopefully this he see why all the real. Now, let's switch gears and talk about recommender system. Recommended system for more than 20 years. There's a tremendous progress on the model, the machine learning model. Inspire. Wide open area in this massive scale of the problem. In sometimes despair to stay the progress on the scale of the data has outgrown the progress. What do they say,? The system has to work out? Please recommend a system

has two of the Mind. And I really have multiple different recommenders, different ways. Interest on a loan. The best place to hunt. Recommendation. if I come from, What is what is it? I'd like to see how that one goes about the catalog takes each product on Tuesday. Then a clock timer serving time in general. How do you create a product? Maybe you are thinking that are various ways. That's why you can just send me a pic. There are two things that we like to use that we have in pictures.

Ended up in Borger. Brotherhood of the operations defined as a contact Mission. Linen, bedding and the girl from Stockton, That's what brings a part of this album. How do you use? So? I'm home. Music station. The meaning of innovation. I showed you how to paint them bedding and how to retrieve them. I'm both combined. That's So Raven, Port Beach. Let's talk about how about you? Come ashore? You probably called what is called. Tell me something,, you can select the arms that knows

what is a multi-armed bandit. We can have the template. And why we like to do expiration because the population. Can you get rid of your experiments and we, and we have seen? But these are not my talk in summary. And above all. Find inspiration in Biscoe. Thank you all and sorry for the technical difficulties. Do I have time for question? I don't actually here, so I don't know. Baby, I just read that question. Myself and thank you for the distribution. Yeah, we got the same.

It is about. Thank you all, have a good rest of the day.

Cackle comments for the website

Buy this talk

Access to the talk “Shopping Recommendations at Pinterest”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Ticket

Get access to all videos “MLconf Online 2020”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Ticket

Interested in topic “Artificial Intelligence and Machine Learning”?

You might be interested in videos from this event

February 4 - 5, 2021
Online
26
106
ai, application, bot, chatbot, conversation, data, design, healthcare, ml

Similar talks

Agustín Mautone
Machine Learning Engineer at Tryolabs
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Sophie Watson
Senior Data Scientist at Red Hat
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Meghana Ravikumar
Machine Learning Engineer at SigOpt
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Buy this video

Video
Access to the talk “Shopping Recommendations at Pinterest”
Available
In cart
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free
Free

Conference Cast

With ConferenceCast.tv, you get access to our library of the world's best conference talks.

Conference Cast
949 conferences
37757 speakers
14408 hours of content