Presented By O'Reilly and Cloudera
Make Data Work
September 25–26, 2017: Training
September 26–28, 2017: Tutorials & Conference
New York, NY

Deep learning for recommender systems

Mo Patel (Independent), Junxia Li (Think Big Analytics)
9:00am12:30pm Tuesday, September 26, 2017
Artificial Intelligence, Machine Learning & Data Science
Location: 1A 18 Level: Intermediate
Secondary topics:  Deep learning, ecommerce

Who is this presentation for?

  • Data scientists and engineers

Prerequisite knowledge

  • Basic familiarity with TensorFlow training APIs
  • A working knowledge of Python, linear algebra, matrix operations, and recommendation systems

Materials or downloads needed in advance

  • A laptop with the ability to SSH into a server and a browser that can connect to Jupyter notebooks on servers (GPU-powered servers will be provided for use in training models with the Movie Lens dataset installed; if your laptop has an NVIDIA GPU, you can download the Movie Lens dataset.)

What you'll learn

  • Learn how to train deep learning models for categories and weighted alternated least square models for exceptions
  • Learn how to build models in Python using TensorFlow, test TensorFlow models, and visualize models with TensorBoard

Description

Recommendation systems are increasingly important in our digital world, and many organizations are looking to machine learning to create recommendations that leverage their unique datasets to provide better results. Most applications have used techniques best described as wide learning: logistic regression and minhash and weighted alternated least squares (WALS). In the last two years, deep learning applications have been put into production, and many leading digital companies are using deep learning to create recommendation models, simplifying feature engineering and improving performance.

Junxia Li and Mo Patel demonstrate how to apply deep learning to improve consumer recommendations by training neural nets to learn categories of interest for recommendations using embeddings. You’ll also learn how to achieve wide and deep learning with WALS matrix factorization—now used in production for the Google Play store. Focusing on memorization and generalization enables you to build machine learning models that serve both fine- and coarse-grained objectives.

Topics include:

  • Concepts for wide and deep models
  • Training a wide and deep recommendation model with TensorFlow on the Movie Lens dataset, using a deep learning model using a neural net with embeddings
  • Measuring model performance
  • Visualizing model behavior
  • A wide learning model using TensorFlow MLToolkit’s WALS matrix factorization
  • Wide and deep learning combining both techniques
  • Further applications of wide and deep learning
Photo of Mo Patel

Mo Patel

Independent

Mo Patel is an independent deep learning consultant advising individuals, startups, and enterprise clients on strategic and technical AI topics. Mo has successfully managed and executed data science projects with clients across several industries, including cable, auto manufacturing, medical device manufacturing, technology, and car insurance. Previously, he was practice director for AI and deep learning at Think Big Analytics, a Teradata company, where he mentored and advised Think Big clients and provided guidance on ongoing deep learning projects; he was also a management consultant and a software engineer earlier in his career. A continuous learner, Mo conducts research on applications of deep learning, reinforcement learning, and graph analytics toward solving existing and novel business problems and brings a diversity of educational and hands-on expertise connecting business and technology. He holds an MBA, a master’s degree in computer science, and a bachelor’s degree in mathematics.

Photo of Junxia Li

Junxia Li

Think Big Analytics

Junxia Li is a senior data scientist at Think Big Analytics, a Teradata company, where she focuses on solving recommendation problems using the latest techniques like deep and wide learning across clients from several verticals. Junxia has successfully implemented advanced machine learning models for clients from a number of different industries, such as automotive, telecommunications, and retail. Junxia is enthusiastic about emerging advancements in machine learning, especially deep learning and AI, and she enjoys reading cutting-edge research papers and experimenting with new ideas. She holds a master’s degree in business and IT and a dual bachelor’s degree in economics and information systems.

Comments on this page are now closed.

Comments

Picture of Mo Patel
Mo Patel | DEEP LEARNING CONSULTANT
09/26/2017 5:57am EDT

The contest will be posted here: https://github.com/datadynamo/strata_ny_2017_recommender_tutorial

Shrinath Parikh | LEAD BIG DATA ANALYTICS ENGINEER
09/26/2017 5:31am EDT

Can provide the GitHub link or access to the tutorial (DataSet, Instructions, PPT)? Many members could not attend this due to conflict.

Thanks!