Book Image

Machine Learning: Make Your Own Recommender System

By : Oliver Theobald
Book Image

Machine Learning: Make Your Own Recommender System

By: Oliver Theobald

Overview of this book

With an introductory overview, the course prepares you for a deep dive into the practical application of Scikit-Learn and the datasets that bring theories to life. From the basics of machine learning to the intricate details of setting up a sandbox environment, this course covers the essential groundwork for any aspiring data scientist. The course focuses on developing your skills in working with data, implementing data reduction techniques, and understanding the intricacies of item-based and user-based collaborative filtering, along with content-based filtering. These core methodologies are crucial for creating accurate and efficient recommender systems that cater to the unique preferences of users. Practical examples and evaluations further solidify your learning, making complex concepts accessible and manageable. The course wraps up by addressing the critical topics of privacy, ethics in machine learning, and the exciting future of recommender systems. This holistic approach ensures that you not only gain technical proficiency but also consider the broader implications of your work in this field. With a final look at further resources, your journey into machine learning and recommender systems is just beginning, armed with the knowledge and tools to explore new horizons.
Table of Contents (15 chapters)
Free Chapter
1
FOREWORD
2
DATASETS USED IN THIS BOOK
3
INTRODUCING SCIKIT-LEARN
4
INTRODUCTION
5
THE ANATOMY
6
SETTING UP A SANDBOX ENVIRONMENT
7
WORKING WITH DATA
8
DATA REDUCTION
9
ITEM-BASED COLLABORATIVE FILTERING
10
USER-BASED COLLABORATIVE FILTERING
11
CONTENT-BASED FILTERING
12
EVALUATION
13
PRIVACY & ETHICS
14
THE FUTURE OF RECOMMENDER SYSTEMS
15
FURTHER RESOURCES

FOREWORD

 

Recommender systems dictate the stream of content displayed to us each day and their impact on online behavior is second to none. From relevant friend suggestions on Facebook to product recommendations on Amazon, there’s no missing their presence and online sway. Whether you agree or disagree with this method of marketing, there’s no arguing its effectiveness. If mass adoption doesn’t convince you, take a look at what you’ve recently viewed and bought online. There’s a strong chance that at least some of your online activities, including finding this book, originated from algorithm-backed recommendations.

These data-driven systems are eroding the dominance of traditional search while aiding the discoverability of items that might not otherwise have been found. As a breakaway branch of machine learning, it’s more important than ever to understand how these models work and how to code your own basic recommender system.

This book is designed for beginners with partial background knowledge of data science and machine learning, including statistics and computing programming using Python. If this is your first foray into data science, you may want to spend a few hours reading my first book Machine Learning for Absolute Beginners before you get started here.