Topics: AI | Data Science | Data Visualization | Deep Learning | Machine Learning | NLP | Python | R | Statistics

KDnuggets Home » News :: 2013 :: Aug :: Publications :: LIONbook Chapter 6: Rules, decision trees, and forests ( 13:n20 )

LIONbook Chapter 6: Rules, decision trees, and forests

The LIONbook on machine learning and optimization, written by co-founders of LionSolver software, is provided free on a chapter by chapter basis for personal and non-profit usage. This chapter provides a clear explanation of the most popular machine learning methods.

Here is the latest chapter from LIONbook, a new book dedicated to “LION” combination of Machine Learning and Intelligent Optimization, written by the developers of LionSolver software, Roberto Battiti and Mauro Brunato.

This book will available for free from the web, chapter after chapter.

Here are previous chapters:

and the latest,

LIONbook Chapter 6: Rules, decision trees, and forestsChapter 6: Rules, decision trees, and forests

Rules are a way to condense nuggets of knowledge in a way amenable to human understanding.

  • If “customer is wealthy” then “he will buy my product.”
  • If “body temperature greater than 37 degrees Celsius” then “patient is sick.”

Decision rules are commonly used in the medical field, in banking and insurance, in specifying processes to deal with customers, etc.

… Decision trees have been popular since the beginning of machine learning. Now, it is true that only small and shallow trees can be “understood” by a human, but the popularity of decision trees is recently growing with the abundance of computing power and memory.

Many, in some cases hundreds of trees, can be jointly used as decision forests to obtain robust classifiers. When considering forests, the care for human understanding falls in the background, the pragmatic search for robust top-quality performance without the risk of overtraining comes to the foreground.

Sign Up

By subscribing you accept KDnuggets Privacy Policy