Building Recommender Systems with Machine Learning and AI: Help people discover new products and content with deep learning, neural networks, and machine learning recommendations.

Description

Learn how to build recommender systems from one of Amazon's pioneers in the field. Frank Kane spent over nine years at Amazon, where he managed and led the development of many of Amazon's personalized product recommendation technologies. This updated second edition covers the latest developments in the field from Google and Amazon, and the latest research in applying deep neural networks to recommender systems. You've seen automated recommendations everywhere - on Netflix's home page, on YouTube, and on Amazon as these 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 the largest, most prestigious tech employers out there, and by understanding how they work, you'll become very valuable to them. This book is adapted from Frank's popular online course published by Sundog Education, so you can expect lots of visual aids from its slides and a conversational, accessible tone throughout the book. The graphics and scripts from over 350 slides are included, and you'll have access to all of the source code associated with it as well. We'll cover tried and true recommendation algorithms based on neighborhood-based collaborative filtering, and work our way up to more modern techniques including matrix factorization and even deep learning with artificial neural networks. Along the way, you'll learn from Frank's extensive industry experience to understand the real-world challenges you'll encounter when applying these algorithms at large scale and with real-world data. This book is very hands-on; you'll develop your own framework for evaluating and combining many different recommendation algorithms together, and you'll even build your own neural networks using Tensorflow to generate recommendations from real-world movie ratings from real people. We'll cover:Building a recommendation engineEvaluating recommender systemsContent-based filtering using item attributesNeighborhood-based collaborative filtering with user-based, item-based, and KNN CFModel-based methods including matrix factorization and SVDApplying deep learning, AI, and artificial neural networks to recommendationsSession-based recommendations with recursive neural networksScaling to massive data sets with Apache Spark machine learning, Amazon DSSTNE deep learning, and AWS SageMaker with factorization machinesUsing the Tensorflow Recommenders Framework (TFRS) to develop and deploy deep learning-based recommender systemsUsing SaaS platforms such as Amazon Personalize, Recombee, and RichRelevanceUsing Generative Adversarial Networks (GAN's) to generate user recommendationsReal-world challenges and solutions with recommender systemsCase studies from YouTube and NetflixBuilding hybrid, ensemble recommendersThis comprehensive book takes you all the way from the early days of collaborative filtering, to bleeding-edge applications of deep neural networks and modern machine learning techniques for recommending the best items to every individual user . The coding exercises for this book use the Python programming language. We include an intro to Python if you're new to it, but you'll need some prior programming experience in order to use this book successfully. We also include a short introduction to deep learning, Tensorfow, and Keras if you are new to the field of artificial intelligence, but you'll need to be able to understand new computer algorithms. Dive in, and learn about one of the most interesting and lucrative applications of machine learning and deep learning there is! Getting Started Introduction Getting Set Up Course Overview What Is a Recommender System? Overview of Recommender Systems Applications of Recommender Systems Gathering Interest Data Top-N Recommenders Quiz Introduction to Python Evaluating Recommender Systems Testing Methodologies Accuracy Measures Hit Rate Measures Coverage Diversity Novelty Churn Responsiveness A/B Tests Quiz Measuring Recommenders with Python Recommender Engine Design Content-Based Filtering Attribute-based Recommendations Cosine Similarity K-Nearest Neighbors Coding Activity A Note on Implicit Ratings. Bleeding Edge Alert! Mise en Scène Similarities Coding Exercise Neighborhood-Based Collaborative Filtering Top-N Architectures Cosine Similarity Sparsity Adjusted Cosine Pearson Similarity Spearman Rank Correlation Mean Squared Difference Jaccard Similarity User-based Collaborative Filtering Coding Activity Item-Based Collaborative Filtering Coding Activity KNN Recommenders Coding Activity Bleeding Edge Alert! Translation-Based Recommendations Model-Based Methods Matrix Factorization Principal Component Analysis Coding Activity: SVD Flavors of Matrix Factorization Coding Exercise Bleeding Edge Alert! Sparse Linear Methods Recommendations with Deep Learning Introduction to Deep Learning Deep Learning Pre-requisites Artificial Neural Networks Deep Learning Networks Using TensorFlow Using Keras Convolutional Neural Networks Recurrent Neural Networks Generative Adversarial Networks (GAN’s) Coding Exercise Recommendations with Deep Learning Restricted Boltzmann Machines Coding Exercise Deep Neural Networks for Recommendations Autoencoders Coding Activity Using RNN’s for Session-Based Recommendations Coding Exercise Bleeding Edge Alert! Generative Adversarial Network Recommenders Bleeding Edge Alert! Deep Factorization Machines Word2Vec 3D CNN’s Scaling it Up Apache Spark and MLLib Coding Activity Amazon DSSTNE Coding Activity AWS SageMaker Other Systems of Note Amazon Personalize Recombee PredictionIO RichRelevance System Architectures for Deployment Challenges of Recommender Systems The Cold-Start Problem Exercise: Random Exploration Stoplists Filter Bubbles Trust Outliers and Data Cleaning Malicious User Behavior The Trouble with Click Data International Considerations The Effects of Time Optimizing for Profit Case Studies YouTube Learning to Rank Netflix Hybrid Recommenders Coding Exercise More to Explore Let’s Stay in Touch About the Author