Evolutionary Decision Trees in Large-Scale Data Mining

Description

This book presents a unified framework, based on specialized evolutionary algorithms, for the global induction of various types of classification and regression trees from data. The resulting univariate or oblique trees are significantly smaller than those produced by standard top-down methods, an aspect that is critical for the interpretation of mined patterns by domain analysts. The approach presented here is extremely flexible and can easily be adapted to specific data mining applications, e.g. cost-sensitive model trees for financial data or multi-test trees for gene expression data. The global induction can be efficiently applied to large-scale data without the need for extraordinary resources. With a simple GPU-based acceleration, datasets composed of millions of instances can be mined in minutes. In the event that the size of the datasets makes the fastest memory computing impossible, the Spark-based implementation on computer clusters, which offers impressive fault tolerance and scalability potential, can be applied. Front Matter ....Pages i-xi Front Matter ....Pages 1-1 Evolutionary Computation (Marek Kretowski)....Pages 3-20 Decision Trees in Data Mining (Marek Kretowski)....Pages 21-48 Parallel and Distributed Computation (Marek Kretowski)....Pages 49-68 Front Matter ....Pages 69-69 Global Induction of Univariate Trees (Marek Kretowski)....Pages 71-99 Oblique and Mixed Decision Trees (Marek Kretowski)....Pages 101-113 Front Matter ....Pages 115-115 Cost-Sensitive Tree Induction (Marek Kretowski)....Pages 117-129 Multi-test Decision Trees for Gene Expression Data (Marek Kretowski)....Pages 131-142 Front Matter ....Pages 143-143 Parallel Computations for Evolutionary Induction (Marek Kretowski)....Pages 145-174 Back Matter ....Pages 175-180