Hands-On Recommendation Systems with Python: Start building powerful and personalized, recommendation engines with Python

by Rounak Banik

With Hands-On Recommendation Systems with Python, learn the tools and techniques required in building various kinds of powerful recommendation systems (collaborative, knowledge and content based) and deploying them to the web Recommendation systems are at the heart of almost every internet business today; from Facebook to Netflix to Amazon. Providing good recommendations, whether it's friends, movies, or groceries, goes a long way in defining user experience and enticing your customers to use your platform. This book shows you how to do just that. You will learn about the different kinds of recommenders used in the industry and see how to build them from scratch using Python. No need to wade through tons of machine learning theory—you'll get started with building and learning about recommenders as quickly as possible.. In this book, you will build an IMDB Top 250 clone, a content-based engine that works on movie metadata. You'll use collaborative filters to make use of customer behavior data, and a Hybrid Recommender that incorporates content based and collaborative filtering techniques With this book, all you need to get started with building recommendation systems is a familiarity with Python, and by the time you're fnished, you will have a great grasp of how recommenders work and be in a strong position to apply the techniques that you will learn to your own problem domains. If you are a Python developer and want to develop applications for social networking, news personalization or smart advertising, this is the book for you. Basic knowledge of machine learning techniques will be helpful, but not mandatory.

Genres: Programming, Computer Science

146 pages, Paperback

Published July 31, 2018

About the author

Rounak Banik is a Young India Fellow and an ECE graduate from IIT Roorkee. He has worked as a software engineer at Parceed, a New York start-up, and Springboard, an EdTech start-up based in San Francisco and Bangalore. He has also served as a backend development instructor at Acadview, teaching Python and Django to around 35 college students from Delhi and Dehradun.

He is an alumni of Springboard's data science career track. He has given talks at the SciPy India Conference and published popular tutorials on Kaggle and DataCamp.

Reviews

[Keyo Çalî · Rating 3 out of 5]

If you have to make a recommendation system in a short time, and practically you know nothing about recommenders, then this is the book for you!
It was fun, but I had to watch lots of youtube videos to understand the concepts and the math behind many things the author just uses as a "black box".

and hey,
I made a simple recommender system!
You pick a movie, and it recommends some books
isn't it interesting?!
I used Goodreads API to download the book descriptions

and here it is the link to the notebook from Kaggle.

[CrunchyApple · Rating 3 out of 5]

This book provides an overview of the recommendation systems in an easy fashion. It provides basic concepts, practical codes, and rich examples to illustrate the ideas.

It is very easy to digest the content given little to no experience in machine learning concepts, including regression, classification, clustering, similarity score, natural language processing, and measurements. With all these techniques, recommendation systems are built.

Different types of recommendation systems are introduced and illustrated with examples. The memory-based, the model-based, and the hybrid recommendations are included.

Crucial algorithms like Funk-SVD (Singular Vector Decomposition) are written in a layman's fashion. I personally take it as a good introduction to them and will need other materials for more in-depth knowledge.

Overall, I think it is a good introduction book for recommendation systems. As the author said, it is to prepare you to learn more. It is obviously indicating that more effort is needed to become an expert.

[Kate · Rating 3 out of 5]

Good, but dated, which means a bunch of the (later chapters, surprise package) code does not work anymore.

Also the cosine_sims CSV file for me gets well over 25GB and then I canceled building it because I think it should be under 2GB, so something's probably wrong there too.

If you create separate .py files for each chapter/concept/recommender, it gets super confusing because the new recommender uses old some files/code from previous chapters.

[Xianshun Chen · Rating 2 out of 5]

The book is too simple to be of any use to me. It may be useful for someone who does not have any background in ML or data mining and wants to learning some basic technique but it is not a good book to learn recommender system from my perspective.

[Mashfiqur Rahman aninda · Rating 4 out of 5]

A quick starter for getting a hang of recommendation systems working. It does not deep into mathematical concepts but brushes the basics effectively.
Corresponding codes can be found on https://github.com/Mashfiqur-Rahman/h...

[Özgür · Rating 3 out of 5]

An easy to follow entry level text on recommender systems.
Misses the latest and more sophisticated model based methods e.g. NN's, matrix factorization, graph based models.
Overall an easy read to warm up to the subject.

[Bhavani Shankar · Rating 5 out of 5]

A window

This book is like a window or a door for naive people like me who just got idea to learn or do a project on Recommendation systems but dont know where to start or confused. For those who are not an expert in Machine learning etc.