Data Mining: Opportunities and Challenges

Chapter I: A Survey of Bayesian Data Mining

Table 1: Outcomes for men, women, and men+women in a clinical trial

Table 2: Customer types in a recommender system

Table 3: Individual's access records

Table 4: Probabilities of assignments of types to customers

Chapter II: Control of Inductive Bias in Supervised Learning Using Evolutionary Computation-A Wrapper-Based Approach

Table 1: Five time series representations and their prescriptive metrics

Table 2: Hierarchical committee machines (combiners) and their prescriptive metrics

Table 3: Performance of a HME-type mixture model compared with that of other inducers on the crop condition monitoring problem

Table 4: Results from Jenesis for One Company (5-way cross validation), representative data sets

Chapter IV: Feature Selection in Data Mining

Table 1: Results of Experiment 1

Table 2: Summary of Experiment 2. The hit rates of three different models are shown over the top 50% of prospects

Table 3: The average classification accuracy (%) with standard error of five runs of ELSA/EM and greedy search. The "-" entry indicates that no solution is found by ELSA/EM. The last row and column show the number of win-loss-tie (W-L-T) cases of ELSA/EM compared with greedy search

Table 4: Experimental results of MEE/ANN

Chapter V: Parallel and Distributed Data Mining through Parallel Skeletons and Distributed Objects

Table 1: Software development costs for Apriori, DBSCAN and C4.5: Number of lines and kind of code, development times, best speedup on different target machines

Chapter VI: Data Mining Based on Rough Sets

Table 1: Consistent data set

Table 2: Inconsistent data set

Table 3: Classification table

Table 4: Probabilistic decision table

Table 5: Input data for LERS

Chapter VII: The Impact of Missing Data on Data Mining

Table 1: Illustration of Hot Deck Imputation: Incomplete data set

Table 2: Illustration of Hot Deck Imputation: Imputed data set

Table 3: Illustration of Regression Imputation

Chapter VIII: Mining Text Documents for Thematic Hierarchies Using Self-Organizing Maps

Table 1: The intra-and extra-hierarchy distances of every hierarchy developed from CORPUS-1 and CORPUS-2. The root node columns show the neuron indices of the root node of each hierarchy

Table 2: The ranks of all themes over all terms for all hierarchies

Chapter X: Maximum Performance Efficiency Approaches for Estimating Best Practice Costs

Table 1: British rates departments data based on Dyson and Thanassoulis (1988). Efficiency rating based on model MDE-2 with preemptive positive weights modification

Table 2: Descriptive statistics for the derived data, Y_r

Table 3: Descriptive statistics estimated from 100 simulated data sets

Chapter XI: Bayesian Data Mining and Knowledge Discovery

Table 1: Titanic example data set

Table 2: Fragment of Titanic data set

Chapter XIII: Query-By-Structure Approach for the Web

Table 1: Test results

Table 2: Hamming network vs. commercial search engine result comparison

Chapter XIV: Financial Benchmarking Using Self-Organizing Maps-Studying the International Pulp and Paper Industry

Table 1: The included companies

Table 2: Examples of trained 7x5 maps

Table 3: Cluster descriptions

Chapter XV: Data Mining in Health Care Applications

Table 1: IT Implementation process model from Cooper and Zmud (1990)

Table 2: Summary of findings across cases

Chapter XVI: Data Mining for Human Resource Information Systems

Table 1: Data collected by an HRIS

Table 2: Functional use of data collected by an HRIS

Table 3: Examples of HR related questions

Chapter XVII: Data Mining in Information Technology and Banking Performance

Table 1: Numerical example

Table 2: Data for 15 banks

Table 3: Banking performance

Table 4: IT and banking performance

Table 5: Optimal accounts and transactions

Chapter XVIII: Social, Ethical and Legal Issues of Data Mining

Table 1: Benefits of data mining

Table 2: Drawbacks of data mining

Table 3: U.S. Federal Regulations that impact privacy (Adapted from Caudill & Murphy, 2000)

Table 4: Issues surrounding data mining that are open for debate despite legal developments

Chapter XIX: Data Mining in Designing an Agent-Based DSS

Table 1: Data associated with each query

Table 2: Logical structure of data for a query q_i

Table 3: Logical structure of data for the example

Table 4: Logical structure of data for the domain d_j