Many business decisions are made in the absence of complete information about the decision consequences. Credit lines are approved without knowing the future behavior of the customers; stocks are bought and sold without knowing their future prices; parts are manufactured without knowing all the factors affecting their final quality; etc. All these cases can be categorized as decision making under uncertainty. Decision makers (human or automated) can handle uncertainty in different ways. Deferring the decision due to the lack of sufficient information may not be an option, especially in real-time systems. Sometimes expert rules, based on experience and intuition, are used. Decision tree is a popular form of representing a set of mutually exclusive rules. An example of a two-branch tree is: if a credit applicant is a student, approve; otherwise, decline. Expert rules are usually based on some hidden assumptions, which are trying to predict the decision consequences. A hidden assumption of the last rule set is: a student will be a profitable customer. Since the direct predictions of the future may not be accurate, a decision maker can consider using some information from the past. The idea is to utilize the potential similarity between the patterns of the past (e.g., "most students used to be profitable") and the patterns of the future (e.g., "students will be profitable").

Comprehensive coverage of recent advances in the application of soft computing and fuzzy logic data mining Also useful as a reference book in data mining, machine learning, fuzzy logic, and artificial intelligence

Klappentext
The volume offers a comprehensive coverage of the recent advances in the application of soft computing and fuzzy logic theory to data mining and knowledge discovery databases. It focuses on some of the hardest, and yet unsolved, issues of data mining like understandability of patterns, finding complex relationships between attributes, handling missing and noisy data, mining very large datasets, change detection in time series, and integration of the discovery process with database management systems.

Inhalt
Data Mining with Neuro-Fuzzy Models.- Granular Computing in Data Mining.- Fuzzification and Reduction of Information - Theoretic Rule Sets.- Mining Fuzzy Association Rules in a Database Containing Relational and Transactional Data.- Fuzzy Linguistics Summaries via Association Rules.- The Fuzzy-ROSA Method: A Statistically Motivated Fuzzy Approach for Data-Based Generation of Small Interpretable Rule Bases in High-Dimensional Search Spaces.- Discovering Knowledge from Fuzzy Concept Lattice.- Mining of Labeled Incomplete Data Using Fast Dimension Partitioning.- Mining a Growing Feature Map by Data Skeleton Modelling.- Soft Regression - A Data Mining Tool.- Some Practical Applications of Soft Computing and Data Mining.- Intelligent Mining in Image Databases, with Applications to Satellite Imaging and to Web Search.- Fuzzy Genetic Modeling and Forecasting for Nonlinear Time Series.