Building Recommender Systems with Machine Learning and AI
Frank Kane
  • Course duration: 9h 13m
You've seen automated recommendations everywhere—on Netflix's home page, on YouTube, and on Amazon. Now build your own recommendation systems to help people discover new products and content, using deep learning, neural networks, and machine learning. In Building Recommender Systems with Machine Learning and AI, you’ll learn from Frank Kane, who led the development of many of Amazon's recommendation technologies, and unlock one of the most valuable applications of machine learning today.

Distributed by Manning Publications

This course was created independently by big data expert Frank Kane and is distributed by Manning through our exclusive liveVideo platform.

About the subject

You've seen automated recommendations everywhere—on Netflix's home page, on YouTube, and on Amazon. To accomplish this, machine learning algorithms learn about your unique interests and show the best products or content for you as an individual. These technologies have become central to both prestigious tech employers and enterprises of all sizes, and by understanding how they work, you'll become very valuable to them.

About the video

Learn how to build recommender systems from Frank Kane, one of Amazon's pioneers in the field of ML-based recommender systems. In Building Recommender Systems with Machine Learning and AI, you’ll cover tried and true recommendation algorithms based on neighborhood-based collaborative filtering, and work your way up to more modern techniques such as matrix factorization and even deep learning with artificial neural networks. As you go, you’ll develop your own framework for evaluating and combining many different recommendation algorithms together and build your own neural networks using Tensorflow to generate recommendations from movie ratings data. Along the way, you'll learn from Frank's extensive industry experience to understand the challenges you'll encounter when applying these algorithms at large scale and with real-world data.
Table of Contents detailed table of contents

Getting started

Install Anaconda, course materials, and create movie recommendations!

Course roadmap

Types of recommenders

Understanding you through implicit and explicit ratings

Top-N recommender architecture

[Quiz] Review the basics of recommender systems

Introduction to Python

The basics of Python

Data structures in Python

Functions in Python

Booleans, loops and a hands on challenge

Evaluating Recommender Systems

Train/Test and cross validation

Accuracy metrics (RMSE, MAE)

Top-N hit rate - many ways

Coverage, diversity, and novelty

Churn, responsiveness, and A/B tests

[Quiz] Review ways to measure your recommender

[Activity] Walkthrough of

[Activity] Walkthrough of

[Activity] Measure the performance of SVD recommendations

A Recommender Engine Framework

Our recommender engine architecture

Recommender engine walkthrough, Part 1

Recommender engine walkthrough, Part 2

Review the results of our algorithm evaluation.

Content-based filtering

Content-Based Recommendations,and the Cosine Similarity Metric

K-Nearest-Neighbors and Content Recs

[Activity] Producing and Evaluating Content-Based Movie Recommendations

[Activity] Bleeding Edge Alert! Miseen Scene Recommendations

[Exercise] Dive Deeper intoContent-Based Recommendations

Neighborhood-based collaborative filtering

Measuring similarity, and sparsity

Similarity metrics

User-based collaborative filtering

[Activity] User-based collaborative filtering, hands-on

Item-based collaborative filtering

[Activity] Item-based collaborative filtering, hands-on

[Exercise] Tuning collaborative filtering algorithms

[Activity] Evaluating collaborative filtering systems offline

Measure the hit rate of item-based collaborative filtering


[Activity] Running user and item-based KNN on MovieLens

14. [Exercise] Experiment with different KNN parameters.

Bleeding edge alert! Translation-based recommendations

Matrix factorization methods

Principal component analysis (PCA)

Singular value decomposition

[Activity] Running SVD and SVD++ on MovieLens

Improving on SVD

[Exercise] Tune the hyper parameters on SVD

Bleeding edge alert! Sparse Linear Methods (SLIM)

Introduction to deep learning [Optional]

Deep learning introduction

Deep learning pre-requisites

History of artificial neural networks

[Activity] Playing with Tensorflow

Training neural networks

Tuning neural networks

Introduction to Tensorflow

[Activity] Handwriting recognition with Tensorflow, part 1

[Activity] Handwriting recognition with Tensorflow, part 2

[Activity] Handwriting recognition with Tensorflow, Part 3

Introduction to Keras

[Activity] Handwriting recognition with Keras

Classifier patterns with Keras

[Exercise] Predict political parties of politicians with Keras

Intro to Convolutional Neural Networks (CNN’s)

CNN architectures

[Activity] Handwriting recognition with Convolutional Neural Networks (CNNs)

Intro to Recurrent Neural Networks (RNN’s)

Training recurrent neural networks

[Activity] Sentiment analysis of movie reviews using RNN’s and Keras

Deep learning for recommender systems

Intro to deep learning for recommenders

Restricted boltzmann machines (RBM’s)

[Activity] Recommendations with RBM’s, part 1

[Activity] Recommendations with RBM’s, part 2

[Activity] Evaluating the RBM recommender

[Exercise] Tuning restricted Boltzmann machines

Exercise Results: Tuning a RBM recommender

Auto-Encoders for recommendations: Deep learning for Recs

[Activity] Recommendations with deep neural networks

Clickstream recommendationswith RNN’s

[Exercise] Get GRU4Rec working on your desktop

Exercise Results: GRU4Rec in action

Bleeding edge alert! Deep factorization machines

More emerging tech to watch

Scaling it up

[Activity] Introduction and installation of Apache Spark

Apache Spark architecture

[Activity] Movie recommendations with Spark, matrix factorization, and ALS

[Activity] Recommendations from 20 million ratings with Spark


DSSTNE in Action

Scaling Up DSSTNE

AWS SageMaker and factorization machines

SageMaker in action: Factorization machines on one million ratings, in the cloud

Real-world challenges of recommender systems

The cold start problem (and solutions)

[Exercise] Implement random exploration

Exercise solution: Random exploration


[Exercise] Implement a stoplist

Exercise solution: Implement a stoplist

Filter bubbles, trust, and outliers

[Exercise] Identify and eliminate outlier users

Exercise solution: Outlier removal

Fraud, The perils of clickstream, and international concerns

Temporal effects, and value-aware recommendations

Case studies

Case study: YouTube, Part 1

Case study: YouTube, Part 2

Case study: Netflix, Part 1

Case study: Netflix, Part 2

Hybrid approaches

Hybrid recommenders and exercise

Exercise Solution: hybrid recommenders

Wrapping up

More to explore


For experienced software developers or computer scientists.

What you will learn

  • Building a recommendation engine
  • Content-based filtering using item attributes
  • Neighborhood-based collaborative filtering with user-based, item-based, and KNN CF
  • Model-based methods including matrix factorization and SVD
  • Applying deep learning, AI, and artificial neural networks to recommendations
  • Case studies from YouTube and Netflix

About the instructor

Frank Kane holds 17 issued patents in the fields of distributed computing, data mining, and machine learning. He spent 9 years at Amazon and IMDb, developing and managing the technology that automatically delivers product and movie recommendations to millions of customers every day. Sundog Software, his own company specializing in virtual reality environment technology and teaching others about big data analysis, is his pride and joy.

placing your order...

Don't refresh or navigate away from the page.
liveVideo $49.99 $99.99
Building Recommender Systems with Machine Learning and AI (liveVideo) added to cart
continue shopping
go to cart

Prices displayed in rupees will be charged in USD when you check out.