Download Slide 1 - Management Support System

Mata Kuliah
: CSM 211 , Management Support System
Tahun Akademik : 2014/2015
BUSINESS INTELLIGENT :
DATA WAREHOUSE , DATA AQUITITION
, DATA MINING , BUSINESS ANALYTICS
DAN VISUALIZATION
Pertemuan-5
5-1
Sasaran Pembelajaran
• Describe issues in data collection, problems and quality
• Describe the characteristic and organization of database
management systems
• Explain the importance and use of a data warehouse and datamart
• Describe business intelligence/business analytics and their
importance to organizations
• Describe how online analytical processing (OLAP), data mining,
data visualization, multidimensionality, and real-time analytics can
improve decision making
• Explain how the web impacts database technologies and methods
and vice versa
• Describe how database technologies and methods as part of
business intelligence/business analytics improve decision making
• Describe web intelligence/web analytics and their importance to
organizations
5-2
Hasil Pembelajaran
The student can shows relationship between
Database Management Systems (DBMS) to
Decision Support System (DSS)
5-3
Data, Information, Knowledge
• Data
– Items about thins, eventy, activities, and transaction
are recorded, classified, and stored but not organized
to convey any specific meaning
– Source from internal or external
• Information
– Data that have been organized in a manner that gives
meaning for the recipient
• Knowledge
– Consists of data items, information organized and
process to convety understanding, experience,
accumulated learning that are applicable to current
problem / activities
5-4
Database Management System (DBMS) in
Decision Support System/Business
Intelligence
1. Software to management database
2. Operating in operation systems to
management data (create, update,
delete, etc)
3. Need Query and management reporting
4. Data Security
5. Need programming language to
construction Decision Support Systems
5-5
Database Organization and Structures
• Hierarchical Database
– Top down, like inverted tree
– Fields have only one “parent”, each “parent”
can have multiple “children”
– Fast
• Network Database
– Relationships created through linked lists,
using pointers
– “Children” can have multiple “parents”
– Greater flexibility, substantial overhead
5-6
Database Organization and Structures
• Relational Database
– Flat, two-dimensional tables with multiple
access queries
– Examines relations between multiple tables
– Flexible, quick, and extendable with data
independence
• Object Oriented Database
– Data analyzed at conceptual level
– Inheritance, abstraction, encapsulation
5-7
Database Organization and Structures
• Multimedia Based Database
– Multimedia Database Management System
(MMDBMS) manage data in variety of format
• Document Based Database
– Electronic Document Management (EDM) systems
• Intelligent Database
– Artificial Intelligence (AI) technologies, Web based
intelligent agent and Artifical Neural Network (ANN),
simplify access to manipulation of complex database
5-8
Database Structures
5-9
DATA WAREHOUSE
• Needed support DSS to analysis the big
data from other resource by quick result
and supporting critical processes
• Data warehouse Aspect :
- Characterics data warehouse
- Arsitecture data
- Data warehouse development
5-10
Characterics of Data Warehousing
1.
2.
3.
4.
5.
6.
7.
8.
Subject Oriented
Integrated
Time Variant (time series)
Nonvolatile
Summarized
Non Normalized
Sources
Metadata
5-11
ARCHITECTURE OF A 3TIER DATA
WAREHOUSE
5-12
ARCHITECTURE OF A 2 TIER DATA WAREHOUSE
5-13
Data Warehouse Development
The process of migrating data to data
warehouse involves :
The extraction of data from all relevant
sources
Data sources may consist of files extracted
from OLTP databases, spreadsheets, personal
database (microsoft access), external files
All of the input file are written to a set of
staging table which are designed to facilitate
the load process
5-14
DATA MARTS
• Data marts is a subset of the data warehouse, typically
consisting of a single subject area (example : Marketing,
Operations, Finance).
• Type of Data marts :
– Dependent (replicated) :
• Created from warehouse
• Replicated
• Functional subset of warehouse
– Independent :
• Scaled down, less expensive version of data warehouse
• Designed for a department or SBU (Sub Business Unit)
• Organization may have multiple data marts
• Difficult to integrated
5-15
ADVANTAGES OF DATA MARTS
• The cost if low in comparison to an enterprise data
warehouse
• The lack time for implementation is significantly
shortes
• Controlled locally rather centerly
• Less information than the data warehouse
• Allow a business unit to build its own decision
support systems without relying on a centralized IS
Department
• An independent data mart can serve as a proof of
concept prior to investing the resources needed to
develop a comprehensive enterprise data warehouse
5-16
DATA MINING
• Data mining (DM) is a term used to describe knowledge
discovery in databases.
• DM is a process that uses statistical, mathematical,
artificial intelligence and machine learning techiques to
extract and identify useful information and subsequent
knowledge from large databases.
• Type methods to identify patterns in data :
– Simple models (SQL based query, OLAP, Human
judgement)
– Intermediate models (regression, decision tree,
clustering)
– Complex Models (neural networks, other rule
5-17
induction)
DATA MINING TOOLS AND TECHNIQUES
• Statistical Methods
Linear an non linear regression, point estimation
• Decision Trees
Used to classification and clustering methods
• Case Base Reasoning
Using historical case
• Neural Computing
Utilize many connected noteds
5-18
DATA MINING TOOLS AND TECHNIQUES
• Intelligent agents
approaches to retrieving information from
databases, especially external ones is the use of
intelligent agents
• Genetic Algorithms
Work on the principle of expansion of possible
outcomes
• Other Tools
Several other tools can be used
5-19
Data Visualization
• Data visualization is easier to implement when
the necessary data are in a data warehouse or
better yet in a multidimensional server
• Technology that supporting data visualization
and interpretation of :
– Digital imaging, GIS, GUI, tables,
multidimensions, graphs, VR, 3D, animation
– Identify relationships and trends
• Data Manipulation can get with good
performance
5-20
Multidimensionality
• Summary data can be organized in different
ways for analysis and presentation. An efficient
way to do this called Multi Dimensionality
• Data can organizated with standard, not analysis
• The Factors considered In multidimensionality :
– Dimensions (product, salespeople ,market,
business units)
– Measures (sales volume, money, inventory,
profit, forecasting vs actual)
– Time(daily, weekly, monthly, quarterly, yearly)
• Significant overhead and storage
5-21
Real-Time Analytics
The User need specialized methods to store
information in many format with :
– Query analysis Real-time
– Decision making Real-time
– Update data warehouses Real-time
• Updates may be made while queries are
active
• Not all data updated continuously
– Consolidated in business application
analytics
5-22
GEOGRAPHIC INFORMATION SYSTEMS (GIS)
• GIS is a computer based system for capturing,
storing, checking, integrating, manipulating,
and displaying data with digitized maps :
– Orientation geographic
– Maps model geographic
– Needs a software web access to maps
– Using with modeling and simulation
• GIS is used as a geographic spreadsheet that
allows manager to model business activities
and performance what if analysis
5-23
GIS APPLICATION
5-24
Web Analytics/Intelligence
• Web Analytics and web intelligence are the terms
used to describe the application of business
analytics / business intelligence of web sites
• Web Analytics
– Business application analytics to activities
operations of web sites
• Web Intelligence
– Business application intelligence analytics to
activities operations of web sites
=========
thanks 4 your attention
=========
5-25