Presented By O’Reilly and Cloudera
Make Data Work
March 5–6, 2018: Training
March 6–8, 2018: Tutorials & Conference
San Jose, CA

Deep learning-based search and recommendation systems using TensorFlow

Abhishek Kumar (Publicis Sapient), Vijay Agneeswaran (Walmart Labs)
1:30pm5:00pm Tuesday, March 6, 2018
Average rating: ****.
(4.00, 3 ratings)

Who is this presentation for?

  • Data scientists, data engineers, data architects, and CxOs

Prerequisite knowledge

  • A basic understanding of machine learning and programming

Materials or downloads needed in advance

  • All notebooks and required data will be provided using a cloud hosted environment. No additional downloads required. Attendees will only require the browser with internet connectivity on their own laptop and TensorFlow installed for this hands-on tutorial

What you'll learn

  • Gain an end-to-end view of deep learning-based recommendation and learning-to-rank systems using TensorFlow


Recommendation systems are all around us. Ecommerce companies like Amazon recommend goods that we are likely to buy based on our past behavior. Netflix suggests what videos we should watch. Pandora even builds personalized music streams, based on what we are likely to listen to. Almost every website has a recommendation system based on user browsing history, past purchases, past searches, and preferences.

It turns out most existing recommendation systems are based on three paradigms: collaborative filtering (CF) and its variants, content-based recommendation engines, and hybrid recommendation engines that combine content-based and CF or exploit more information about users in content-based recommendation. Recommendation systems must be accurate, able to handle sparse data, able to recommend items that have never been rated (cold start), and scalable. The memory-based CF systems are highly scalable but may suffer from cold start and data sparsity problems. Model-based CF systems such as the Naïve Bayes recommendation engine often outperform memory-based CF systems with respect to accuracy. Matrix factorization-based recommendation systems (the most advanced systems) have the best accuracy but may suffer from performance degradation issues at extreme scale. So what’s the solution?

Abhishek Kumar and Vijay Srinivas Agneeswaran offer an introduction to deep learning-based recommendation and learning-to-rank systems using TensorFlow, including model management and scaling. You’ll learn how to build a recommender system based on intent prediction using deep learning that is based on a real-world implementation for an ecommerce client. When users search for products, the system ranks search results based on purchase behavior and other possible sources of data, such as browsing history, domain catalog, and social traits/behavior analysis of the user.

Photo of Abhishek Kumar

Abhishek Kumar

Publicis Sapient

Abhishek Kumar is a senior manager of data science in Publicis Sapient’s India office, where he looks after scaling up the data science practice by applying machine learning and deep learning techniques to domains such as retail, ecommerce, marketing, and operations. Abhishek is an experienced data science professional and technical team lead specializing in building and managing data products from conceptualization to the deployment phase and interested in solving challenging machine learning problems. Previously, he worked in the R&D center for the largest power-generation company in India on various machine learning projects involving predictive modeling, forecasting, optimization, and anomaly detection and led the center’s data science team in the development and deployment of data science-related projects in several thermal and solar power plant sites. Abhishek is a technical writer and blogger as well as a Pluralsight author and has created several data science courses. He’s also a regular speaker at various national and international conferences and universities. Abhishek holds a master’s degree in information and data science from the University of California, Berkeley. Abhishek has spoken at past O’Reilly conferences, including Strata 2019, Strata 2018, and AI 2019.

Photo of Vijay Agneeswaran

Vijay Agneeswaran

Walmart Labs

Dr. Vijay Srinivas Agneeswaran has a Bachelor’s degree in Computer Science & Engineering from SVCE, Madras University (1998), an MS (By Research) from IIT Madras in 2001, a PhD from IIT Madras (2008) and a post-doctoral research fellowship in the LSIR Labs, Swiss Federal Institute of Technology, Lausanne (EPFL). He currently heads data sciences R&D at Walmart Labs, India. He has spent the last eighteen years creating intellectual property and building data-based products in Industry and academia. In his current role, he heads machine learning platform development and data science foundation teams, which provide platform/intelligent services for Walmart businesses across the world. In the past, he has led the team that delivered real-time hyper-personalization for a global auto-major as well as other work for various clients across domains such as retail, banking/finance, telecom, automotive etc. He has built PMML support into Spark/Storm and realized several machine learning algorithms such as LDA, Random Forests over Spark. He led a team that designed and implemented a big data governance product for a role-based fine-grained access control inside of Hadoop YARN. He and his team have also built the first distributed deep learning framework on Spark. He is a professional member of the ACM and the IEEE (Senior) for the last 10+ years. He has five full US patents and has published in leading journals and conferences, including IEEE transactions. His research interests include distributed systems, artificial intelligence as well as Big-Data and other emerging technologies.

Comments on this page are now closed.


Picture of Vijay Agneeswaran
03/13/2018 3:21pm PDT

Dhruv, the slides have been uploaded on the conference page. Kindly let me know if you can see it or I can share the link directly.

Picture of Dhruv Choudhary
03/06/2018 3:53am PST

Hi, I wanted to attend this session, but seems like I may not be able to make it – Will you be posting the materials for participants to access ?


Picture of Vijay Agneeswaran
12/13/2017 12:26pm PST

Sorry, forgot that you asked about Safari. Found one book in safari which may be of interest:

Picture of Vijay Agneeswaran
12/11/2017 2:10pm PST

The deep learning book by Bengio is of course the best 1. The book on Recommender systems 2 by Charu Agarwal is also relevant. Few other articles such as 3 or 4 are also good. Hope this helps.

1 Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville, the MIT Press, Cambridge.

2 Recommender Systems by Charu. C. Aggrwal, Springer International Publishing.


4 Paul Covington, Jay Adams, and Emre Sargin. 2016. Deep Neural Networks for YouTube Recommendations. In Proceedings of the 10th ACM Conference on Recommender Systems(RecSys ’16). ACM, New York, NY, USA, 191-198.

12/08/2017 7:22am PST

This is for the beginners who are willing to ‘stretch…,’ can you recommend some books (or courses on safari) to prep for this session? Thanks!!