الفهرس 
Data Mining in Business IntelligencOnly 14 pages are availabe for public view
 |  | from | 119 |  |  |
| | | from | 119 | | |
Abstract
Business intelligence (BI) is a set of theories, methodologies, architectures, and technologies that transform raw data into meaningful and useful information for business purposes. Common functions of business intelligence technologies are reporting, online analytical processing (OLAP), data mining, process mining, business performance management, benchmarking, text mining and predictive analytics.Business failure prediction is one of the most effective problems in the field of finance. The main target of research in this application is to develop classification models to distinguish between failed and none—failed firms. Such models are important to financial decision makers (credit managers, managers of firms, investors, etc.); they serve as early warning systems of the failure probability of a corporate entity.A lot of methods have been used in the past for the prediction of business failure like Discriminant analysis, Logit analysis, Quadratic Function, etc. Although some of these methods lead to models with a satisfactory ability to discriminate between healthy and failing firms. These approaches are only good for crisp types of data sets. If the values of data continuous or uncertain, we must apply fuzzy theory.In this thesis, some of data mining techniques are used to analyze data of the banking system. The proposed data model aims to find decision rules that identify the behaviors of customers that can cause bankruptcy.The proposed data model is composed of two phases. In the first phase, the data are clustered using K-means, fuzzy K-means and Self-Organizing Map methods. Then the best clustering method is chosen. By choosing the best clustering method, appropriate data table with conditions and decisions attributes is found. The second phase is to develop variable consistency of dominance rough set approach as a classification method to extract the minimum cover rules. The induced rules can provide recommendation of behaviors that increase the risk in financial process. Finally a comparison among variable consistency of dominance rough set, classical rough set and C4.5 methods are done to show the differences.The aim of this study is to mine data regarding customers in the banking system. In this thesis, we present a framework to create an early warning system to avoid business failure in the bank system.