DATA MINING Desktop Survival Guide by Graham Williams
Desktop Survival Project Home Rattle Introduction Getting Started Interacting with Rattle Data Exploring Data Test Transforming Data Cluster Analysis Data Graphics in R Understanding Data Preparing Data Descriptive and Predictive Analytics Issues Evaluating Models Reporting Cluster Analysis Text Mining Text Mining Algorithms Bagging Bayes Classifier Cluster Analysis Conditional Trees Hierarchical Clustering K-Nearest Neighbours Linear Models Neural Networks Support Vector Machines Open Products AlphaMiner Borgelt Data Mining Suite KNime R Rattle Weka Closed Products C4.5 Clementine Equbits Foresight GhostMiner InductionEngine ODM Enterprise Miner Statistica Data Miner TreeNet Virtual Predict Appendicies Installing Rattle Glossary Bibliography Index

C

C5.0: A commercial decision tree and rule induction product from RuleQuest developed by Ross Quinlan as the successor to his very successful and widely used ID3 and C4.5 systems.

Churn: The process of customer turnover, as occurs in many consumer service providers such as telecommunications and credit providers.

Classification:

Coevolution: An Refer[evolutionary-computation]Evolutionary Computation paradigm where both the measure of fitness and the solution evolve separately and affect each other.

Computational Intelligence: Describes numerically based Artificial Intelligence systems distinguished from Symbolic Intelligence. Generally covers Refer[evolutionary-computation]Evolutionary Computation, Neural Networks and Fuzzy Logic.

Cross Validation: A method of comparing or confirming performance of predictive models by estimating the error that would be produced by a model. Cross validation is also used to compare one method of inducing a predictive model (called an inducer) with another inducer. Cross validation can also be used to refine the parameters of a particular inducer. In this case the inducer's parameters are refined to minimise the error in the model produced. A k-fold cross validation will build k models from k datasets.

Confidence:

Cubist: A commercial piecewise-linear regression product from Refer[rulequest]RuleQuest developed by Ross Quinlan. Uses decision tree induction to identify subsets of the data on which to perform regression.

Support further development through the purchase of the PDF version of the book.
PDF version is properly formatted and forms a comprehensive book (draft with over 700 pages).
Brought to you by Togaware. This page generated: Tuesday, 23 December 2008