AI at Scale in Rakuten’s Recommendation

We're excited to welcome Rakuten Group Inc. as a partner company supporting MLT and the machine learning community. Principal Data Science Engineer Phuc Le from Rakuten will talk about how AI/ML is applied at scale in the e-commerce industry.
Phuc will give a general introduction about recommendation systems. He will dive into some modern types of recommendations used in Rakuten Group services. He will close his talk by explaining how multi-task learning with deep learning helps to improve buy-again recommendations.

📌 About:
MLT is an award-winning non-profit organization in Tokyo and a machine learning community of more than 10,000 members consisting of researchers, engineers, and ML enthusiasts.
Rakuten is one of Japan’s top e-commerce companies founded in 1997 and provides 70+ different services with 1.6 billion members across the world. (https://global.rakuten.com/corp/about/)

👉 SESSION STRUCTURE
19:00 - 19:10: Quick introduction of MLT & Rakuten
19:10 - 19:50: Recommendation Systems & MTL
19:50 - 20:00: QA time and Feedback survey
* The timings mentioned above are in JST. Please use the following link to confirm your time zone.
https://www.worldtimebuddy.com/?pl=1&lid=1850147,8,5,6&h=1850147&hf=1

👉 JOIN ZOOM
TBA

📌 Prerequisites
Recommended reads:
Recommending What Video to Watch Next (youtube)
Modeling labels for conversion value prediction (Google)

👉 PRESENTER BIO
Phuc Le is a Principal Data Science Engineer at AI Product Supervisory Department of Rakuten Group Inc. He got his PhD. from the Tokyo Institute of Technology, Japan in 2012 and his thesis was about Quantum Computation. In 2010, he was awarded the Young Researcher Award from IEEE Computational Intelligence Society, Japan Chapter for his works on extending Image Processing on Quantum Computers. From 2012 to 2015, he worked for NetMile Inc. as a full-stack engineer where he helped to build a whole recommendation system for affiliate advertising from scratch for the company. Since 2015, he has worked on various large-scaled recommendation systems for many services both in Japan and abroad of Rakuten Group Inc. He also has several patents on recommendation system domains.
Linkedin: https://jp.linkedin.com/in/phuc-le-68b005bb

● MLT NEWSLETTER
Sign up for the (infrequent and low noise) newsletter if you'd like to stay up to date with events and what we're working on https://www.getrevue.co/profile/mltai

● MLT PATRON
Become an MLT Patron and help us to keep MLT meetups like this inclusive and for free. https://www.patreon.com/MLTOKYO

● FIND MLT RESOURCES
Github: https://github.com/Machine-Learning-Tokyo
Youtube: https://www.youtube.com/MLTOKYO
Slack: https://bit.ly/36ImxtW

● RECRUITING
MLT events are for community building and knowledge sharing. We politely ask that company representatives, recruiters, and consultants looking to hire or sell their services do not participate in MLT activities or approach members in any form.

● CODE OF CONDUCT
MLT promotes an inclusive environment that values integrity, openness, and respect. https://github.com/Machine-Learning-Tokyo/MLT_starterkit