Product Description

Want to tap the power behind search rankings, product recommendations, social bookmarking, and online matchmaking? This fascinating book demonstrates how you can build Web 2.0 applications to mine the enormous amount of data created by people on the Internet. With the sophisticated algorithms in this book, you can write smart programs to access interesting datasets from other web sites, collect data from users of your own applications, and analyze and understand the data once you've found it. "Programming Collective Intelligence" takes you into the world of machine learning and statistics, and explains how to draw conclusions about user experience, marketing, personal tastes, and human behavior in general - all from information that you and others collect every day. Each algorithm is described clearly and concisely with code that can immediately be used on your web site, blog, Wiki, or specialized application.This book explains: collaborative filtering techniques that enable online retailers to recommend products or media; methods of clustering to detect groups of similar items in a large dataset; search engine features - crawlers, indexers, query engines, and the PageRank algorithm; optimization algorithms that search millions of possible solutions to a problem and choose the best one; bayesian filtering, used in spam filters for classifying documents based on word types and other features; using decision trees not only to make predictions, but to model the way decisions are made; predicting numerical values rather than classifications to build price models; support vector machines to match people in online dating sites; non-negative matrix factorization to find the independent features in a dataset; and, evolving intelligence for problem solving - how a computer develops its skill by improving its own code the more it plays a game. Each chapter includes exercises for extending the algorithms to make them more powerful. Go beyond simple database-backed applications and put the wealth of Internet data to work for you. 'Bravo! I cannot think of a better way for a developer to first learn these algorithms and methods, nor can I think of a better way for me (an old AI dog) to reinvigorate my knowledge of the details' - Dan Russell, Google. 'Toby's book does a great job of breaking down the complex subject matter of machine-learning algorithms into practical, easy-to-understand examples that can be directly applied to analysis of social interaction across the Web today. If I had this book two years ago, it would have saved precious time going down some fruitless paths' - Tim Wolters, CTO, Collective Intellect.

Product Details

• Amazon Sales Rank: #47979 in Books
• Published on: 2007-08-16
• Original language: English
• Number of items: 1
• Binding: Paperback
• 334 pages

London Perl M(ou)ngers, london.pm.org, December 2007
..you should buy this book.... It's well written manual that'll handily expand your repetoire.

About the Author
Toby Segaran is a software developer and manager at Genstruct, a computational systems biology company. He has written free web applications for his own use and put them online for others to try, including: tasktoy, a task management system; Lazybase, an online application that lets users design, create and share databases of anything they like; and Rosetta Blog, an online tool for practicing Spanish and French by reading blogs along with their translations and lists of common words. Each of these has several hundred regular users. His blog is located at kiwitobes.com.

Customer Reviews

excellent - accessible machine learning
This is excellent - forget the marketing rubbish about making better web 2.0 apps: It is all about machine learning - the science of how Amazon and others can make recommendations based on the ordering patterns of others.

The difference between it and other texts on this machine learning, is how accessible it is, and how apt the data sets it chooses are. Machine learning is an active area of research, and I was surprised that this book even covers kernel methods.

It generates a real appetite to learn more about the theory of machine learning: Which you will need, as most machine learning text books are mathematically tough going and dry.

I only wish I could skip the day job for a week and study this book from cover to cover.

A truly outstanding book
This book is definitely worth having on your bookshelf. It breaks down one of the most complex and demanding subjects into delightful, succinct and digestible pieces.

Having dredged my way through similar books in the past, I wasn't expecting too much, but Programming Collective Intelligence is remarkable. I found this book gripping; completing each example was very rewarding, and has now got me hooked on learning more.

I ended up working my way through the entire book, and really feel that it was time well spent. I now feel that I actually understand the concepts and algorithms surrounding machine learning/AI/data mining, and as a bonus have become familiar with a huge number of web 2.0 APIs.

The source code is almost impeccable. Most programming books falter on sloppy and/or incomplete code, but Programming Collective Intelligence is well explained and has the complete Python code written in the book, as well as being available for download. I was able to do every example without any major problems, despite having never used the Python language before.

Well written & diagrammed, with good examples and wonderful explanations: this a fantastic book, and to be highly recommended.

Poor attempt
Whilst the book starts out positively enough (hence the 1 review star), it quickly degenerates into a rambling disorganised text that neither adequately covers collective intelligence, programming nor build smart web 2.0 applications.

Terms and assumptions are used without explanation, important issues are skimmed over lightening speed yet simple issues are repeated ad-nausem.

A better title might be "A light skim over Collective Intelligence for Python Programmers", but anything else is seriously overselling the confusing and frustratingly sparse content.