Recommender systems have started to play a pivotal role in our daily life. From recommending jobs, movies and restaurants to finding partners, recommender systems have been predicting the user preferences that they will be interested in.
Below here, we have listed eight best online resources, in no particular order, that will help you learn and build your own recommender systems.
Basic Recommender Systems
About: Basic Recommender Systems is a course provided by Coursera. Here you will learn the leading approaches in recommender systems. The techniques described here include both collaborative and content-based approaches and include the most important algorithms used to provide recommendations. You’ll learn how they work, how to use and how to evaluate them, pointing out the benefits and limits of different recommender system alternatives.
Read more here.
Best Practices on Recommendation Systems
About: Best Practices on Recommendation Systems is a repository in GitHub provided by Microsoft. In this repo, you will find examples and best practices for building recommendation systems provided as Jupyter notebooks. The examples detail five key tasks, which include, preparing data, modelling, evaluating, model selection and optimising and operationalising.
Read more here.
Building Recommender Systems with ML and AI
About: In this course, Building Recommender Systems with machine learning and AI, you will learn how to build recommender systems with neural networks and Restricted Boltzmann Machines (RBM’s), create recommendations using deep learning at massive scale, build a framework for testing and evaluating recommendation algorithms with Python. You will also build recommender systems with matrix factorisation methods such as SVD and SVD++, use K-Nearest-Neighbors to recommend items to users and more.
Read more here.
Beginner Tutorial: Recommender Systems in Python
About: Here, you will learn the steps that are needed to build a recommendation engine using Python language. You will learn from building basic models to content-based and collaborative filtering recommender systems. You will also learn the steps to build a basic model of content-based recommender systems that will help in getting started with building more complex models.
Read more here.
Recommender Systems: Evaluation and Metrics
About: In this tutorial course, you will understand the steps to evaluate recommender systems. You will also understand how various metrics relate to different user goals as well as business goals. You will get knowledge with numerous families of metrics, including the measure prediction accuracy, rank accuracy, decision-support, as well as other factors such as diversity, product coverage, among others. You will also acquire how to rigorously handle offline evaluations, such as how to prepare and sample data, how to aggregate results, etc..
Read more here.
Recommender Systems and Deep Learning in Python
About: In this course, you will learn various tricks that will help to build recommender systems work across multiple platforms. You will learn and implement recommendations for your users using simple and state-of-the-art algorithms, big data matrix factorisation on Spark with an AWS EC2 cluster, matrix factorisation / SVD in pure Numpy, matrix factorisation, deep neural networks, residual networks, and autoencoder in Keras, among others.
Read more here.
Build a Recommendation Engine With Collaborative Filtering
About: This tutorial will help in learning how to build a recommendation engine using Python language. The topics include collaborative filtering and its types, data needed to build a recommender, libraries available in Python to build recommenders and lastly, the use cases and challenges of collaborative filtering.
Read more here.
Recommender Systems Specialisation
About: This course, Recommender Systems Specialisation on Coursera covers all the fundamental techniques in recommender systems, from non-personalised and project-association recommenders through content-based and collaborative filtering techniques. It also covers advanced topics, such as matrix factorisation, hybrid ML methods for recommender systems, and dimension reduction techniques for the user-product preference space.
Read more here.
