Managing Data Mining Technologies in Organizations: Techniques and Applications

Chapter 1: Bayesian Networks as a Decision Support Tool in Credit Scoring Domain

Table 1: Probability table P(<Customer Category>)

Table 2: Probability table P(<Customer Category >|<Debit>)

Table 3: Stages of credit granting process

Table 4: Areas of enterprise analysis

Table 5: The scoring table for the "profitability" area (normative point scale)

Table 6: The scoring tables for the rest of the objective factors areas

Table 7: Subjective factors, scoring tables

Table 8: The score corresponding to the class of the economic-financial position

Table 9: The score corresponding to the class of the economic-financial position and the previous credit performance

Table 10: Example-The score corresponding to factors

Table 11: The total score corresponding to qualitative and quantitative factors

Table 12: Conditional probability distributions in "quality of management" node

Table 13: The factors considered in Bayesian network structure of credit scoring system

Chapter 3: An Evolutionary Misclassification Cost Minimization Approach for Medical Diagnosis

Table 1: Results of tests of difference in means for training and holdout samples

Table 2: Results of tests in training and holdout samples of heart disease data

Table 3: Results for tests in training and holdout samples for BUPA data set

Chapter 4: Guiding Knowledge Discovery Through Interactive Data Mining

Table 1: Textual presentation of clustering algorithm results

Table 2: Layered interaction model (Nielson, 1992)

Chapter 5: A Proposed Process for Performing Data Mining Projects

Table 1: Mapping observed activities to straw man

Chapter 6: Data Mining for Optimal Combination Demand Forecasts

Table 1: Summary statistics of the 26 items

Table 2: The alternative forecasting methods in each procedure

Table 3a: Forecasting results for sample A of 8 items

Table 3b: Forecasting results for sample B of 2 items

Table 4a: Results for common forecasting methods for sample A items

Table 4b: Results for common forecasting methods for sample B items

Table 5: F-statistics and comparisons of forecast error variances

Table 6: Results for common weights and forecasting method

Table 7: Summary of results

Table 8: A comparison of ARl and seasonal AR1 for the 10 items

Table 9: Summary of results if Holt-Winters method replaces Holt's method

Chapter 9: Utilization of Data Mining Techniques to Detect and Predict Accounting Fraud: A Comparison of Neural Networks and Discriminant Analysis

Table 1: Predicted group membership

Table 2: Percent good parts of neural net testing

Chapter 12: Combination Forecasts Based on Markov Chain Monte Carlo Estimation of the Mode

Table 1: Results for case 1 simulation study

Table 2: Results for case 2 simulation study

Table 3: Autocorrelation coefficients of arrival series

Table 4: Results of individual forecast method

Table 5: Results of combination forecast methods

Table 6: RMSE values of all the forecasting methods

Chapter 14: Connectionist and Evolutionary Models for Learning, Discovering and Forecasting Software Effort

Table 1: A few major software project failures in US and in UK

Table 2: Performance of three different structural designs during the training phase

Table 3: Performance of three different networks during the test phase

Table 4: Pair-wise comparison (t-test) results for difference in means for actual and predicted software effort

Table 5: Pair-wise comparison (t-test) results for difference in means for actual and predicted software effort