Learning Objectives• Decision Making• Decision Models• Types of Decision Making• Decision Support Systems (DSS)• Types of DSS• Group Decision Support Systems (GDSS)• Data Warehousing• Data Analysis using Data Warehouse• Data Mining• Data Mining Tools
Decision Making• Decision making is the study of identifying and choosing alternatives based on the values and preferences of the decision maker.• Decision making is the process of sufficiently reducing uncertainty and doubt about alternatives to allow a reasonable choice to be made.
Styles of Decision Making• Optimizing: This helps in selecting the best possible alternative for a decision problem. This style involves: – Identification of a problem – Generating alternatives – Selecting the best alternative – Implementing the best alternative – Feedback• Satisficing• Organizational• Political• Maximax• Maximin
Decision Making Procedure• Identify the decision problem keeping the goals in mind.• Get the facts.• Develop alternatives.• Evaluate each alternative.• Rate the risk of each alternative.• Make the decision.
The Modeling Process Analysis Model Results Interpretation AbstractionSymbolic World Real World Management Intuition Decisions Situation
Modeling Characteristics• A model is a simplified representation of a real-world situation.• The advantages of a model are: – The cost of modeling is less – Models enable compression of time – Manipulation of model is much simpler and easier – Testing a model is easier – It is easy for the decision-maker to understand – There is less risk when experimenting with a model than with the real system. – Mathematical models enables testing of large data sets
Types of Models Model Type Characteristics Examples Tangible Easy to Comprehend Car or Aero plane orPhysical Model Difficult to Duplicate and Share House or Building Models Difficult to Modify and Manipulate Limited Scope of Use Intangible Tough to Comprehend Road Map, Speedometer,Analog Model Easy to Duplicate and Share Bar or Pie Chart Easy to Modify and Manipulate Wider Scope of Use Intangible Tough to Comprehend Simulation Model,Symbolic Model Easy to Duplicate and Share Algebraic Model, Easy to Modify and Manipulate Spreadsheet Model Widest Scope of Use
Types of Decision Making• Business decision making is mainly of three types: – Decisions taken under conditions of certainty (Structured Decisions) – Decisions taken under conditions of risk (Semi- Structured Decisions) – Decisions taken under conditions of uncertainty (Un-structured Decisions)
Characteristics of Decision Types The decision-making environmentCharacteristics Certainty Risk UncertaintyControllable variables Known Known KnownUncontrollable variable Known Probabilistic UnknownType of model Deterministic Probabilistic Non-probabilisticType of decision Best Informed UncertainInformation type Quantitative Quantitative and Qualitative QualitativeMathematical tools Linear Statistical methods; Decision analysis; Programming Simulation Simulation
Decision Support Systems (DSS)• Decision Support System (DSS) is an interactive computer-based information system that supports a decision.• The primary function of a DSS is to assist managers in solving unstructured, semi- structured and structured decision problems.• DSS primarily supports analytical, quantitative type of work using modeling techniques.
Characteristics of DSS• The major characteristics of DSS would include:• For semi-structured and Unstructured decisions• For managers at different levels• For groups and individuals• For Adaptable and flexible decisions• Effectiveness, not efficiency the focus• Humans control the machine• Modeling & Knowledge based – Communication DSS – Data-Driven DSS – Document-Driven DSS – Knowledge-Driven DSS – Model-Driven DSS
Group Decision Support Systems• GDSS is an interactive computer-based system that facilitates solution of unstructured decision problems by decision makers working as group.• Organizations decision making process is individual or group driven.• DSS systems are widely used by individuals and the GDSS is meant to be used by the Group decision processes.
Advantages of Group Decision Process• Increased participation• Improved pre-planning• Open, collaborative atmosphere• Idea generation free of criticism• Groups are better than individuals at understanding problems• People are accountable for decisions that they are participating in• Group has more information (Knowledge) than individual• Group members will have their egos embedded in the decision• Better and easy implementation
Problems of Group Decision Process• Time consuming and slow process• Lack of coordination• Poor planning of meetings• Inappropriate influence of group dynamics like fear to speak• Tendency toward compromised solutions of poor quality• Tendency to repeat what already was said• Larger cost of making decision• Inappropriate representation in the group
Data Warehouse• A data warehouse is a subject-oriented, integrated, time-variant and non-volatile collection of data in support of managements decision making process.• Data warehousing provides architectures and tools for business executives to systematically organize, understand, and use their data to make strategic decisions.
Components of Data Warehouse• Subject-oriented.• Integrated.• Time-variant.• Nonvolatile.
Creating Data Warehouse• Source Data/System Identification• Data Warehouse Design and Creation• Data Acquisition• Data Cleansing• Data Aggregation
BI Tools for Data Analysis• Business Intelligence (BI) is a very broad field, which contains technologies such as:• Decision Support Systems (DSS)• Executive Information Systems (EIS)• On-Line Analytical Processing (OLAP)• Relational OLAP (ROLAP)• Multi-Dimensional OLAP (MOLAP)• Hybrid OLAP (HOLAP, a combination of MOLAP and ROLAP)
Components of BI Tool• Multi-dimensional Analysis Tools: Tools that allow the user to look at the data from a number of different "angles". It helps the user to have a 360 degree view of data. These tools often use a multi- dimensional database referred to as a "cube".• Query tools: Tools that allow the user to use SQL (Structured Query Language) queries against the warehouse and get a result.• Data Mining Tools: Tools that automatically search for patterns in data. These tools are usually driven by complex statistical formulas. The easiest way to distinguish data mining from the various forms of OLAP is that OLAP can only answer questions you know to ask, data mining answers questions that one may not be aware of.• Data Visualization Tools: Tools that show graphical representations of data, including complex three-dimensional data pictures. The theory is that the user can "see" trends more effectively in this manner than when looking at complex statistical graphs.
ROLAP Vs. MOLAPCharacteristic ROLAP MOLAPSchema Uses star schema Uses data cubes Additional dimensions can be Additional dimensions require added dynamically re-creation of the data cubeDatabase size Medium to large Small to mediumArchitecture Client/server Client/server Standards-based Proprietary OpenAccess Supports ad hoc requests Limited to predefined Unlimited dimensions dimensionsResources High Very highFlexibility High LowScalability High LowSpeed Good with small data sets; Faster for small to medium average for medium to large data sets; average for large data sets data sets
Data Warehouse Structures• Data warehouse uses the star schema as a data- modeling technique The basic star schema has four components: – Facts: Facts are numeric measurements (values) that represent a specific business aspect or activity. – Dimensions: Dimensions are qualifying characteristics that provide additional perspectives to a given fact. – Attributes: Each dimension table contains attributes. Attributes are often used to search, filter, or classify facts. – Attribute Hierarchies: Attributes within dimensions can be ordered in a well-defined attribute hierarchy.
Data Mining• Data mining tools predict future trends and behaviors, allowing businesses to make proactive, knowledge-driven decisions.• The purpose of data mining is to discover previously unknown data characteristics, relationships, dependencies, or trends.• Data mining is described as a methodology designed to perform knowledge-discovery expeditions over the database data with minimal end user intervention during the actual knowledge-discovery phase.
Data Preparation Stages• Data preparation• Data analysis and classification• Knowledge acquisition• Prognosis
Data Mining Tools• Classes: Stored data is used to locate data in predetermined groups. For example, a retail chain could mine customer purchase data to determine when customers visit and what they typically buy. This information could be used to increase traffic by having special offers for the day.• Clusters: Data items are grouped according to logical relationships or customer preferences. For example, data can be mined to identify market segments or customer affinities.• Associations: Data can be mined to identify associations between the buying patterns. The bread-butter or beer-nuts are examples of associative mining. This helps in doing market-basket analysis.• Sequential patterns: Data is mined to anticipate behavior patterns and trends. It helps in identifying the sequence of purchase. For example, if a customer buys a pen what probability that he/she is going to buy a notebook as its next item.
Data Mining Tools• Decision trees: A structure that can be used to divide up a large collection of records into successively smaller sets of records by applying a sequence of simple decision rules. A decision tree model consists of a set of rules for dividing a large heterogeneous population into smaller, more homogeneous groups with respect to a particular target variable.• Artificial Neural Networks (ANN): Non-linear predictive models that learn through training and resemble biological neural networks in structure. When applied in well-defined domains, their ability to generalize and learn from data “mimics” a human’s ability to learn from experience.• Nearest Neighbor method: In order to predict the prediction value for an unclassified record is, look for similar records and use the prediction value of the record that is nearest to the unclassified record. Records that are near each other will have similar prediction values.• Clustering: Used to segment a database into clusters based on a set of attributes. Clustering governed by measurement of proximity. Members belong to a cluster if they have proximity to each other. The process of grouping data into clusters so that records within a cluster have high similarity in comparison to one another.• Genetic algorithms: Optimization techniques that use process such as genetic combination, mutation, and natural selection in a design based on the concepts of natural evolution.• Rule induction: The extraction of if-then rules from data based on statistical significance.• Data visualization: The visual interpretation of complex relationships in multidimensional data. Graphics tools are used to illustrate data relationships.
Summary• Decision making process is a systematic means of arriving at a decision. It is a way of organizing data with the purpose of presenting or displaying it to the decision maker in such a way that is more obvious than simply making a list of the alternatives.• There are two major approaches to decision making in an organization, the authoritarian method in which an executive figure makes a decision for the group and the group method in which the group decides what to do. Within these two broader approaches, decision makers follow their own style of generating alternatives and taking decisions.• Some of the common styles of decision making include: Optimizing; Satisficing, Organizational, Political, Maximax and Maximin.• Optimizing way of taking decision is the best approach as it helps the decision maker to take the decision in a structured manner.• The three types of models that are popularly being used by decision makers include: physical; analog; and symbolic.• Models created by architect about new building is referred to a physical’ models. Physical models are three-dimensional representations of real-world objects. There are also scaled-down versions of the models which are more suited to computers include (i) analog or graphical models, which use lines, curves, and other symbols to produce flow charts, pie charts, bar charts, scatter diagrams, etc. and (ii) symbolic or mathematical models which use formulae and algorithms to represent real-world situations.• Business decision making is mainly of three types: Decisions taken under conditions of certainty (Structured Decisions); Decisions taken under conditions of risk (Semi-Structured Decisions); and Decisions taken under conditions of uncertainty (Un-structured Decisions).• Decision Support System (DSS) is an interactive computer-based information system that supports a decision. The primary function of a DSS is to assist managers in solving unstructured, semi-structured and structured decision problems.• Typical information that a decision support application might gather and present would be, (a) Accessing all information assets, including legacy and relational data sources; (b) Comparative data figures; (c) Projected figures based on new data or assumptions; (d) Consequences of different decision alternatives, given past experience in a specific context.• The major components that a DSS system would include are User-interface; DSS Data Base; DSS Model Base; and Knowledge Base.
Summary• Five types of DSS includes: data-driven DSS; Model-driven DSS; Communications-driven DSS; Document-driven DSS; and knowledge-driven DSS.• GDSS is an interactive computer-based system that facilitates solution of unstructured decision problems by decision makers working as group. Organizations decision making process is individual or group driven.• A data warehouse is a subject-oriented, integrated, time-variant and non-volatile collection of data in support of managements decision making process. Data warehousing provides architectures and tools for business executives to systematically organize, understand, and use their data to make strategic decisions.• Once the warehouse has been built and populated, it becomes possible to extract meaningful information from it that will provide a competitive advantage and a return on investment. This is done using Business Intelligence (BI) tools. BI is a very broad field, which contains technologies such as Decision Support Systems (DSS), Executive Information Systems (EIS), On-Line Analytical Processing (OLAP), Relational OLAP (ROLAP), Multi-Dimensional OLAP (MOLAP), Hybrid OLAP (HOLAP, a combination of MOLAP and ROLAP), and more.• Data warehouse uses the star schema as a data-modeling technique. It is also used to map multidimensional decision support data into a relational database. The basic star schema has four components: facts, dimensions, attributes, and attribute hierarchies.• Online Analytical Processing (OLAP), create an advanced data analysis environment that supports decision making, business modeling, and operations research activities. OLAP systems share the following characteristics: Use multidimensional data analysis techniques; Provide advanced database support; Provide easy-to-use end user interfaces; and Support client/server architecture. Multidimensional data analysis refers to the processing of data such that data are viewed as part of a multidimensional structure.• Data mining is a powerful technological tool that helps organization in extracting hidden predictive information from large databases. Data mining tools predict future trends and behaviors, allowing businesses to make proactive, knowledge-driven decisions.• Data mining software analyzes relationships and patterns in stored transaction data based on open-ended user queries. Several types of analytical software are available: statistical, machine learning, and neural networks etc. Generally, while mining the data one or more of four types of relationships are sought: classes; clusters; association; and sequencing. Different kind of tools that are popularly being used are: Decision tree; artificial neural network; nearest neighbor; cluster analysis; genetic algorithm; rule induction; and data visualization.