KNOWLEDGE DISCOVERY DATA

KNOWLEDGE DISCOVERY DATA

1. ITERATIVE SEQUENCE OF STEPS

   • DATA CLEANING
   • DATA INTEGRATION
   • DATA SELECTION
   • DATA TRANSFORMATION
   • DATA MINING
     • PROCESS OF DISCOVERING INTERESTING PATTERN AND KNOWLEDGE FROM LARGE AMOUNTS OF DATA
     • DESCRIPTIVES
     • PREDICTIVES
     • DOMAINS
       • STATISTICS
         •  Statistics studies the collection, analysis, interpretation or explanation, and presentation of data  
       • MACHINE LEARNING
         •  Machinelearning investigates how computers can learn (or improve their performance) based on data  
       • PATTERN RECOGNITION
       • DATABASE
       • DATA WAREHOUSE
       • INFORMATION RETRIEVAL
       • VISUALIZATION
       • ALGORITHMS
       • HIGH PERFORMANCE COMPUTING
     • PATTERNS CAN BE MINED DATA MINING FUNCTIONALITIES
       • DISCRIMINATION
         • DISCRIMINATION: COMPARISON OF FEATURES OF ONE CLASS DATA OBJETC AGAINST GENERAL FEATURES OF OBJECTS FROM ONE OR MULTIPLE CLASS OBJECTS CHARACTERIZATION:  summarizing the data of the class under study (often called the target class) in general terms  
       • FREQUEN PATTERNS
         •  There are many kinds of frequent patterns, including frequent itemsets, frequent subsequences (also known as sequential patterns), and frequent substructures.  
         • SUPPORT
         • CONFIDENCE
         • accuracy and coverage
       • ASSOCIATIONS
       • CORRELATIONS
       • CLASSIFICATION AND REGRESSION
         •  Classification is the process of finding a model (or function) that describes and distinguishes data classes or concepts.  Regression analysis is astatistical methodology that is most often used for numeric prediction,   
       • CLUSTERING ANALYSIS AND OULIER ANALYSIS
         •  Unlike classification and regression, which analyze class-labeled (training) data sets, clustering analyzes data objects without consulting class labels.  
       • INTERESTING PATTERNS
         • NOVEL
         • CERTAINTY
         • POTENTIALLY USEFUL
         • EASILY UNSDERSTOOD
         • PATTERN INTERSTINGNESS
           • SUBJECTIVE
           • OBJECTIVE
     • DATA CAN BE MINED
       • DATABASES
       • DATA WAREHOUSES
       • TRANSACTIONAL DATA
       • MANY OTHERS
     • ISSUES OF DATA MINING RESEARCH
       • MINING METHODOLOGIES
       • USER INTERACTION
       • EFFICIENCY AND SCALABILITY
       • DIVERSITY OF DATA TYPES
       • DATA MINING AND SOCIETY
     • VIEWS
       • APPLICATION
       • TECHNOLOGIES
       • DATA
       • KNOWLEDGE
   • PATTERN EVALUATION
     • ¿Interesante?:  (1) easily understood byhumans, (2) valid on new or test data with some degree of certainty, (3) potentiallyuseful, and(4) novel. A pattern is also interesting if it validates a hypothesis that the user sought to confirm.  
   • KNOWLEDGE PRESENTATION

2. APPLICATIONS

   • BUSINESS INTELIGENCE
   • WEB SEARCH
   • BIOINFORMATICS
   • HEALTH INFORMATICS
   • FINANCE
   • DIGITAL LIBRARIES
   • DIGITAL GOVERMENT