Presented By
O’Reilly + Cloudera
Make Data Work
March 25-28, 2019
San Francisco, CA
Please log in

The hitchhiker's guide to deep learning-based recommenders in production

Abhishek Kumar (Publicis Sapient), pramod singh (Walmart Labs )
1:30pm5:00pm Tuesday, March 26, 2019
Average rating: ****.
(4.17, 6 ratings)

Who is this presentation for?

  • Data scientists, ML engineers, executives in data science, and architects



Prerequisite knowledge

  • Familiarity with TensorFlow and recommender systems

What you'll learn

  • Explore deep learning use cases in the enterprise, such as content personalization and recommenders, and the corresponding reference architectures and ML/DL pipelines
  • Learn how to use TensorFlow Serving, MLFlow, Flask, Gunicorn, NGINX, and Locust
  • Understand how to implement CI/CD pipelines for ML and DL


Deep learning has become the de facto AI technique employed in many enterprises to build recommender systems. Deep learning offers the ability to perform auto-feature engineering and handle feature interactions. However, though it’s well understood and most people have started using TensorFlow or PyTorch to build deep learning models, it takes a lot of time and effort and exploration to put deep learning recommender models into production.

Abhishek Kumar and Pramod Singh walk you through deep learning-based recommender and personalization systems they’ve built for clients. Join in to learn how to use TensorFlow Serving and MLflow for end-to-end productionalization, including model serving, Dockerization, reproducibility, and experimentation, and Kubernetes for deployment and orchestration of ML-based microarchitectures. You’ll explore applications of deep learning, such as using LSTM models for forecasting and sequence embedding (and consequently, for predicting the next best action of customers in a personalization context) and using CNNs for image classification. You’ll also see how to do A/B testing to determine the improvement in clickthrough rate and lift for production deployments.

Topics include:

  • Reference architectures for microservices and deep learning-based recommender and content personalization systems
  • How to leverage TensorFlow Serving for model serving and augment it with model management tools
  • How to use MLflow for end-to-end productionalization, including model serving, Dockerization, reproducibility, and experimentation
  • Creating ML and DL APIs using NGINX/Gunicorn for load balancing and deploying ML-based microservices architecture using Docker and Kubernetes
  • Load testing tools such as Locust and how they help in benchmarking ML and DL API performance in a distributed and scalable fashion
  • Creating real-time pipelines using Kafka and Spark Structured Streaming
  • Creating batch pipelines using Apache AirFlow
  • Creating CI/CD pipelines for ML and DL
  • A comparison of this productionization mechanism with Airbnb’s BigHead
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 pramod singh

pramod singh

Walmart Labs

Pramod Singh is a senior machine learning engineer at Walmart Labs. He has extensive hands-on experience in machine learning, deep learning, AI, data engineering, designing algorithms, and application development. He has spent more than 10 years working on multiple data projects at different organizations. He’s the author of three books Machine Learning with PySpark, Learn PySpark, and Learn TensorFlow 2.0. He’s also a regular speaker at major conferences such as the O’Reilly Strata Data and AI Conferences. Pramod holds a BTech in electrical engineering from BATU, and an MBA from Symbiosis University. He’s also done data science certification from IIM–Calcutta. He lives in Bangalore with his wife and three-year-old son. In his spare time, he enjoys playing guitar, coding, reading, and watching football.