Earlier today, I picked up a new book called “Programming Collective Intelligence”. Although I haven’t had much time tonight to read as much as I’d liked, I have managed to sneak in the first couple of chapters. And, I must say, if you are a programmer, marketer, project manager, or pretty much any other person working with products or services and are looking for a way to get more information out of your data, then you need to pick up this book immediately. It’s a book written by Toby Segaran and published thru O’Reilly that not only introduces you to collective intelligence algorithms, but it also dives deep into programming those algorithms using the Python programming language.
The book jumps right in to teaching you how to create a recommendation system for movies. Although the examples provided contain datasets of movies, the book also does a good job of showing you how the same program could be used for other industries such as music, books, and other products. Right from the beginning, Segaran provides you with working code that you can use right out-of-the box with your own datasets. In fact, I just finished reading about how to use the recommendations application to retrieve data from the social bookmarking site Delicious, and offer link recommendations based on what sites other users like.
I hope to find time tomorrow to get thru as many chapters as possible. As I do, I’ll come back here and share some more information I find in the book. Also, the examples in the book require a basic knowledge of Python. But, as I work thru them, I will also be porting the code to C#. I’ll also take some time to port the code to Java as well. That way, I’ll have a good starting point for the algorithms in Python, C#, and Java which I can use in the future no matter which language I might need them in. Besides, I know that a lot of you aren’t experienced Python developers. So, when you pick up this book, and I know you will, you can come back here for translated versions of the code.
Here are the things you can look forward to learning in the book:
- Introduction to Collective Intelligence
- Making Recommendations
- Discovering Groups
- Searching and Ranking
- Document Filtering
- Modeling with Decision Trees
- Building Price Models
- Advanced Classification
- Finding Independent Features
- Evolving Intelligence
This book touches on neural networks, bayesian classifiers, genetic programming, etc… It talks about everything from how to recommend matches on a dating site and even Facebook. It also teaches you how to predict whether someone will signup with your site or whether they will make a purchase or not. There’s even a section that talks about group travel and flights. So, as you can see, this is a book that’s right up my alley and I have a lot of reading to get to.
Until next time, you can (and should) get a copy of this book right now.