You are previewing Data Mining in Public and Private Sectors: Organizational and Government Applications.
O'Reilly logo
Data Mining in Public and Private Sectors: Organizational and Government Applications

Book Description

Data Mining in Public and Private Sectors: Organizational and Government Applications explores the manifestation of data mining and how it can be enhanced at various levels of management. This innovative publication provides relevant theoretical frameworks and the latest empirical research findings.

Table of Contents

  1. Copyright
  2. Foreword
  3. Preface
    1. DATA MINING LINKED TO ORGANIZATIONAL AND GOVERNMENT CONDITIONS
    2. THE BOOK STRUCTURE AND FINAL REMARKS
    3. REFERENCES
  4. 1. Data Mining Studied in Management and Government
    1. 1. Before the Mining Begins: An Enquiry into the Data for Performance Measurement in the Public Sector
      1. ABSTRACT
      2. INTRODUCTION
      3. MEASURING PERFORMANCE IN THE PUBLIC SECTOR
        1. On Which Level Do We Measure The Performances Of The Government?
        2. Do We Measure Perception or Reality?
        3. Which value Indicators Can be used for the Measurement of Public service?
        4. Which Quality guidelines Can be used?
      4. EFFECTS OF PERFORMANCE MEASUREMENT
        1. Introduction and the good side of Performance Measurement
        2. Negative Effects of Performance Measurement
          1. A Too Strong Emphasis on the Easily Quantifiable
          2. Too Little Attention to the Objectives of the Organisation as a Whole
          3. Too Much Attention for ShortTerm Objectives
          4. A Too Strong Emphasis on Criteria for Success
          5. Misrepresentation of Performance
          6. Poor Validity and Reliability
          7. Wrong Interpretations
          8. Gaming
          9. Petrifaction
          10. Reinforces Internal Bureaucracy
          11. Hamper Ambitions/Cherry Picking
          12. Can Punish Good Performance
      5. A GENERAL EXPLANATION OF NEGATIVE EFFECTS AND GLOBAL STRATEGIES TO PREVENT THOSE
      6. CONCLUSION
      7. REFERENCEs
        1. KEY TERMS AND DEFINITIONS
      8. ENDNOTES
    2. 2. Measuring the Financial Crisis in Local Governments through Data Mining
      1. ABSTRACT
      2. INTRODUCTION
      3. HOW SHOULD FINANCIAL CRISES IN LOCAL GOVERNMENT BE MEASURED?
      4. METHODOLOGICAL PROPOSAL: CHAID
        1. Binning Of Continuous Explanatory Variables
        2. Merging Categories for Explanatory variables
        3. Splitting Nodes
      5. RESULTS OF THE MODEL
        1. Support
        2. Response (Confidence)
        3. Index
        4. Gain
        5. Risk Estimates
      6. ANALYZING THE FINANCIAL CONDITION OF LOCAL AUTHORITIES IN SPAIN USING CHAID
        1. Sample
        2. Variables
          1. Dependent Variables Categorized
          2. Descriptive Analysis
      7. ANALYSIS AND RESULTS
        1. Exploratory Analysis
        2. Exploratory Analysis of Correlations; The Most Important Explanatory variables
      8. PREDICTIVE ANALYSIS WITH CHAID: SUCCESS AND FAILURE PROFILES FROM EACH ELEMENT OF FINANCIAL CONDITION
        1. Results Obtained With The Rules for Each Element Of Financial Condition
        2. Goodness of the Element of Financial Condition
      9. CONCLUSION AND DISCUSSION
      10. REFERENCES
        1. KEY TERMS AND DEFINITIONS
      11. ENDNOTES
      12. APPENDIX
      13. APPENDIX 2 (FIGURE 8)
    3. 3. Data Mining Using Fuzzy Decision Trees: An Exposition from a Study of Public Services Strategy in the USA
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Fuzzy set Theory
        2. Fuzzy Decision Trees
        3. Fuzzy Decision Tree Analyses of Example Data set
      4. FUZZY DECISION TREE ANALYSIS OF PUBLIC SERVICES IN THE USA
      5. FUTURE TRENDS
      6. Conclusion
      7. REFERENCES
      8. KEY TERMS AND DEFINITIONS
    4. 4. The Use of Data Mining for Assessing Performance of Administrative Services
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Developing and Organizing Data for Analysis
        2. Structuring the Domain of Investigation
        3. Data Collection and Cleaning
      4. DATA MINING METHOD USED IN THE ANALYSIS
      5. PERFORMANCE ANALYSIS WITH REGRESSION TREES
        1. Impact of Unsolved '96 and New Applications '97 on Productivity '97
        2. Relations between Productivity Trends and Trends of New Applications '98-99
        3. Productivity, Throughput and Education Level of Employees in 1996
        4. Productivity, Throughput and Average Education Level in 1999
        5. Accuracy of Induced Regression Tree Models
      6. HOW FINDINGS MAY HELP TO IMPROVE DECISION MAKING
        1. Useful Findings Concerning Inputs of Administrative Processes
        2. Useful Findings about the Performance of Processes
        3. Useful Findings about outputs of Processes
        4. Testing Current Hypotheses
      7. CONCLUDING REMARKS, FUTURE TRENDS AND SUGGESTED RESEARCH
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    5. 5. Productivity Analysis of Public Services: An Application of Data Mining
      1. ABSTRACT
      2. INTRODUCTION
      3. ASSUMED DRIVERS OF PRODUCTIVITY
        1. Literature on Productivity of Public services
        2. Productivity Drivers of Child Day Care services - Workshop Discussions
      4. RESEARCH METHODS
        1. Data and Measures
        2. Analysis Methods
      5. RESULTS
        1. Description of the Data
        2. Data Mining Results
      6. CONCLUSION
      7. ACKNOWLEDGMENT
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
  5. 2. Data Mining as Privacy, Security and Retention of Data and Knowledge
    1. 6. Perceptions of Students on Location-Based Privacy and Security with Mobile Computing Technology
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. CONCERNS AND ISSUES
      5. RESEARCH AND SOLUTIONS
      6. BACKGROUND QUESTIONS
        1. Objective Questions
        2. Knowledge Questions
        3. Concern and Control Questions
        4. Information Systems vs. Non Information Systems Students
        5. United States vs. European Students
      7. FUTURE TRENDS
        1. Limitations and opportunities
      8. CONCLUSION
      9. REFERENCES
        1. KEY TERMS AND DEFINITIONS
      10. APPENDIX
        1. Framework of Syllabi: Location-Based Privacy with Mobile Computing
          1. Module 1: Architecture and Applications of Mobile Computing
          2. Module 2: Design and Development of Mobile Computing Applications
          3. Module 3: Privacy of Mobile Computing Applications - Enhancement to Syllabi
          4. Module 4: Security of Mobile Computing Architecture and Applications - Enhancement to Syllabi
          5. Module 5: Mobile Computing Societal and Technological Trends
            1. Reference Research Sites for Syllabi
    2. 7. Privacy Preserving Data Mining: How Far Can We Go?
      1. ABSTRACT
      2. INTRODUCTION
      3. Background
      4. MAIN THRUST OF THE CHAPTER
      5. PROTECTING TRADITIONAL SENSITIVE DATA DURING MINING
        1. Perturbative Approaches
        2. Non-Perturbative Approaches
        3. Secure Multiparty Computation Approaches
      6. PROTECTING SENSITIVE PATTERNS FROM MINING
        1. Association Rule Hiding
        2. Classification Rule Hiding
      7. PRIVACY AWARE MOBILITY DATA MINING
        1. Data Perturbation and obfuscation
        2. Secure Multiparty Computation
        3. Sequential Pattern Hiding
      8. FUTURE TRENDS
        1. Privacy-Aware Mobility Data Mining
        2. Privacy Preserving Data Mining
      9. CONCLUSION
      10. REFERENCES
      11. KEY TERMS AND DEFINITIONS
    3. 8. Data Mining Challenges in the Context of Data Retention
      1. ABSTRACT
      2. INTRODUCTION
        1. Definitions
      3. RELATED WORK
      4. DATA STORAGE
        1. Background: Data Warehousing
        2. Email Data Storage Schema
        3. Message Storing
        4. Internet Access Storage Schema
        5. Distributed Architecture
      5. DATA ANALYSiS
        1. False Positives and False Negatives
        2. Data Analysis Example: Inductive Logic Programming
        3. Data Analysis Example: Social Network Analysis
        4. Unbalanced Data in Context of Data Mining
      6. DATA SECURITY ISSUES
        1. Dealing with Distributed Systems
        2. Data Access Control
        3. Data Privacy
      7. COST AND PERFORMANCE ASPECTS
        1. Cost Aspects
        2. Expected Query Response Time
      8. LIMITATIONS IN CONTEXT OF DATA RETENTION
      9. CONCLUSION
      10. REFERENCES
      11. KEY TERMS AND DEFINITIONS
    4. 9. On Data Mining and Knowledge: Questions of Validity
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND: DATA MINING AND INFORMATION SYSTEMS
        1. Information Systems
      4. DATA GENERATION FOR DATABASES
        1. Data Mining
        2. Data Warehouses and Data Marts
      5. KNOWLEDGE AND VALIDITY: A METHODOLOGICAL ORIENTATION FOR DM
        1. Penrose and the Knowledge Term
        2. First Generation Knowledge Management
      6. METHODS FOR KNOWLEDGE GENERATION FROM 'OPERATIONS'
        1. The Rational-Empirical Legacy
        2. DM and the Particular: Methodology for the General
      7. UNCOVERING THE RATIONAL IN QUALITATIVE METHODS
        1. Peculiarities of Qualitative Research
          1. Validity as Quality of Craftsmanship
          2. Communicative Validity
          3. Pragmatic Validity
        2. Positivistic Sciences and the Personal Element
      8. TRENDS OF DM AND KNOWLEDGE: SECURITY AND ORGANISATIONS
        1. Economising and Normalising for Security
        2. A Security oriented Genealogy of organisations
      9. CONCLUSION: DM AND SECURITY OR PREDICTABILITY AND IGNORANCE
      10. REFERENCES
      11. KEY TERMS AND DEFINITIONS
  6. 3. Data Mining in Organizational Situations to Prepare and Forecast
    1. 10. Data Mining Methods for Crude Oil Market Analysis and Forecast
      1. ABSTRACT
      2. INTRODUCTION
      3. DATA MINING METHODS AS A CRUDE OIL PRICE FORECASTING TOOL
      4. BUILDING PROCESS OF MONTHLY CRUDE OIL PRICE FORECASTING MODELS
        1. Model A: A Hybrid Wavelet Decomposition and LSSVM Model for Crude Oil Price Forecasting
          1. Wavelet Decomposition of Original Time Series
          2. Sub-Series Forecasting with LSSVM
          3. Time Series Forecasting Reconstruction
        2. Model B: Forecasting Crude Oil Spot Price by Wavelet Neural Network Using OECD Petroleum inventory Levels
          1. Selection of Model Variables
          2. WNN Approach for Oil Price Series Modeling
      5. EXPERIMENTAL ANALYSIS
        1. Experimental Results Of Model A
          1. Data Description and Structural Breaks Test
          2. Crude Oil Price Series Decomposition
          3. Training and Testing Results
        2. Experimental Results of Model B
          1. Data Preparation and Statistical Analysis
          2. Training and Testing Results
      6. CONCLUSION AND FUTURE DIRECTIONS
      7. ACKNOWLEDGMENT
      8. REFERENCES
      9. KEY TERMS AND DEFINITIONS
    2. 11. Correlation Analysis in Classifiers
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
      4. VARIABLE IMPORTANCE
      5. IMPORTANCE OF THE VALUE OF AN INPUT VARIABLE
      6. INSTANCE CORRELATION BETWEEN AN EXPLANATORY VARIABLE AND THE TARGET CLASS
      7. LEVER VARIABLES
      8. CORRELATION EXPLORATION - METHOD DESCRIPTION
        1. General Case
        2. Exploration of Input Values
        3. Domain of Exploration of Each Variable
        4. Results Ranking
        5. Cases with Class Changes
        6. Case of a Naive Bayesian Classifier
        7. Implementation Details on Very Large Databases
      9. EXPERIMENTATIONS
        1. The Titanic Database - Data and Experimental Conditions
        2. Input Values Exploration
      10. APPLICATION TO SALE: RESULTS ON THE PAKDD 2007 CHALLENGE
        1. Data and Experimental Conditions
        2. Input Values Exploration
      11. APPLICATION TO GOVERNMENT DATA: RESULTS FOR THE CONTRACEPTIVE METHOD CHOICE DATA SET
        1. Data and Experimental Conditions
        2. Input Values Exploration
      12. CONCLUSION AND FUTURE TRENDS
      13. REFERENCES
        1. KEY TERMS AND DEFINITIONS
      14. ENDNOTE
    3. 12. Forecast Analysis for Sales in Large-Scale Retail Trade
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Related Works
          1. Sales Forecasting
          2. Multi-Class Classification with Ordinal Classes
          3. Out of Stock
      4. DATA MINING ON PROMOTIONAL SALES
        1. Data Exploration
        2. Data Preprocessing Issues
          1. Mining Table
        3. Discretization
        4. Predicting the Percentage Variation of Sales
        5. Classification Rules
      5. EVALUATION OF MULTI-CLASS CLASSIFIERS
        1. Problem Definition
        2. Distance from the Diagonal
          1. Example 1
        3. Quantitative Measures
          1. Weights Vector-Based Approach
          2. Limits of the Vector-Based Approach
          3. Vector-Based Accuracy of the Generated Models
          4. Matrix Vector-Based Approach
          5. Example 2
      6. DATA MINING FOR 'OUT OF STOCK' EVENT
        1. Out of Stock Model Definition
        2. Model Construction
      7. DEPLOYMENT AND FUTURE TRENDS
        1. Evaluation and Future Trends
      8. CONCLUSION
      9. REFERENCES
      10. KEY TERMS AND DEFINITIONS
    4. 13. Preparing for New Competition in the Retail Industry
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. How to Fight Competition
      4. GOALS OF THE ANALYSIS
      5. DEVELOPMENT OF THE CONCEPTUAL SOLUTION MODEL
      6. THE DEVELOPMENT OF SCORING MODEL
        1. Interviewing the Users
        2. Defining Key Indicators
        3. Defining the Preprocessing Algorithms
        4. Structural Model Development
        5. Defining the Key Indicator Range
        6. Defining the Rule System
        7. Scoring
          1. "Healthy Life" Segment
          2. "Cleanliness is Next to Godliness" Segment
        8. Integration of Scoring Models into the Existing Information System
      7. DEVELOPMENT OF CUSTOMER CHURN ANALYSIS MODEL
        1. Definition of Customer Churn Analysis Strategy in the Trgovina Company
        2. Preprocessing of the Data for Survival Models
        3. Performing the Analysis
        4. Business Decisions Based on the Analysis
      8. FUTURE TRENDS IN CHURN PREDICTION AND CONCLUSIONS
      9. REFERENCES
      10. KEY TERMS AND DEFINITIONS
  7. 4. Data Mining as Applications and Approaches Related to Organizational Scene
    1. 14. An Exposition of CaRBS Based Data Mining: Investigating Intra Organization Strategic Consensus
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Dempster-Shafer Theory
        2. The Classification and Ranking Belief Simplex (CaRBS) and RCaRBS
      4. MAIN THRUST
        1. Consensus Data Set
        2. CaRBS Analysis
        3. RCaRBS Analysis
      5. FUTURE TRENDS
      6. CONCLUSION
      7. REFERENCES
      8. KEY TERMS AND DEFINITIONS
    2. 15. Data Mining in the Context of Business Network Research
      1. ABSTRACT
      2. INTRODUCTION
      3. THEORETICAL BACKGROUND
        1. Socially Construed Reality and Social Facts
        2. Sociological Paradigms and Conceptual Analysis
      4. MULTILEVEL MODEL AND RESEARCH FRAMEWORK FOR NETWORK-WIDE KNOWLEDGE DISCOVERY
        1. Logical Structure of the Knowledge Discovery Process
        2. Positivistic View: Traditional Data Mining
        3. Possibilities of the Anti-Positivistic View: A Case for Network-Wide Data Mining
        4. Layered Comparison of the Positivistic and Anti- Positivistic Views
      5. MULTIDISCIPLINARY CONCEPT ANALYSIS OF THE DOMAIN AREA
        1. Networks and Business Environments
        2. Net-Like Structures
      6. BUSINESS NETWORKS
      7. GOVERNANCE OF BUSINESS NETWORKS
      8. DOMAIN SPECIFIC BUSINESS NETWORKS: TOURISM INDUSTRY
        1. Organizational Information Technology
      9. DATA, INFORMATION, AND KNOWLEDGE
      10. DATA MINING
        1. Contract Law and Functional Principles
      11. CONTRACTUAL PRINCIPLES
      12. FUNCTIONAL PRINCIPLES
        1. Shared Conceptual Domain Area
      13. INFORMATION ASYMMETRY
      14. INFORMATION INTENSIVE BUSINESS GOVERNANCE
      15. NETWORK-WIDE KNOWLEDGE MANAGEMENT
        1. Network-Wide Knowledge Discovery Research Framework
      16. NETWORK-WIDE KNOWLEDGE DISCOVERY AND COMMUNICATIVE INFORMATION
        1. Anti-Positivistic Characterization of Inter-Organizational Business Information
        2. Information Asymmetry Reduction by Contract Law- Based Functional Principles
          1. Fairness/Equality as Interpretation and Relativity
          2. Good Faith/Fair Dealing Constituting Information Usability
          3. Trust/Confidentiality Increasing Accessibility
      17. KNOWLEDGE DISCOVERY REQUIREMENTS IN IT-BASED TOURISM INDUSTRY NETWORKS
      18. FUTURE TRENDS
        1. Feasibility of Network- Wide Data Mining Approach at Stakeholder Level
        2. Knowledge-Centered Business Network Management
        3. Information-Oriented Network Analysis and Modeling
      19. CONCLUSION
      20. REFERENCES
      21. KEY TERMS AND DEFINITIONS
    3. 16. Clinical Data Mining in the Age of Evidence-Based Practice: Recent Exemplars and Future Challenges
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. How is CDM Different from Conventional Data-Mining, Secondary Analysis and Chart Reviews?
      4. PURPOSES OF CDM IN SOCIAL WORK AND ALLIED HEALTH
      5. THE ADVANTAGES OF USING CDM AS A RESEARCH METHODOLOGY
      6. THE DISADVANTAGES OF CDM AS A RESEARCH METHODOLOGY
      7. BASIC ELEMENTS OF CDM
      8. THE PROCESS OF CDM IN RESEARCH
      9. EXAMPLES OF DIFFERENT TYPES OF CDM STUDIES
        1. Need Studies
        2. Monitoring Studies
        3. CDM Outcomes Studies
      10. THE FUTURE OF CDM IN SOCIAL WORK AND ALLIED HEALTH STUDIES
      11. CONCLUSION
      12. REFERENCES
      13. KEY TERMS AND DEFINITIONS
    4. 17. Data Mining and the Project Management Environment
      1. ABSTRACT
      2. INTRODUCTION
      3. DATA MINING AND THE PROJECT MANAGEMENT ENVIRONMENT CONTEXT
      4. APPLICATION OF DATA MINING: THE PROJECT MANAGEMENT ENVIRONMENT
      5. THE HEART OF THE MATTER: PROCESSES AND THE PROJECTS DATA WAREHOUSE
      6. THE ROAD TO SUCCESS: PROJECT MANAGEMENT SUCCESS (OUTPUTS)
        1. Project Proposal Preparation and Project Scope
        2. Accurate Estimation of Time and Cost to Project Completion
        3. Occupational Health and Safety
        4. Preventative Maintenance of Plant and Equipment
        5. Project Risk Management
        6. Repeatable Project Management Success
      7. THE ROAD TO SUCCESS: PROJECT SUCCESS (OUTCOMES)
        1. Active Project Stakeholders and the Perception of Project Success
        2. Building a Knowledge Warehouse and Developing a Learning Organization
        3. Utilisation of the Knowledge Warehouse
      8. FINAL DESTINATION: PROJECT CORPORATE SUCCESS
        1. Proper Project Selection: Strategic Fit of Projects
        2. Project Portfolio Management: Project Partnerships and Analysis of Project Bids
      9. FUTURE TRENDS
      10. CONCLUSION
      11. REFERENCES
      12. KEY TERMS AND DEFINITIONS
    5. 18. User Approach to Knowledge Discovery in Networked Environment
      1. ABSTRACT
      2. INTRODUCTION
      3. THEORETICAL BACKGROUND AND METHODOLOGY
        1. Complex Adaptive Systems
        2. High-Level Information Exchange Ontology
        3. Methodology
      4. CASE STUDIES
        1. Actor Profile Information
        2. Planning the Mission
        3. Executing Task
        4. Conclusive Findings
      5. CONSEQUENCES FOR KNOWLEDGE DISCOVERY
      6. REFERENCES
      7. KEY TERMS AND DEFINITIONS
  8. Compilation of References
  9. About the Contributors