Академический Документы
Профессиональный Документы
Культура Документы
Submitted To:
By
Ishan Kakkar (2019MBA-13)
Assignment 1
Q1. Discuss various modelling and analysis techniques used in Decision support system.
1. Model
A model is a representation of an actual system. Models embody system characteristics that
are important to the model’s users. At the same time, models simplify reality by eliminating
other characteristics that are not important for their purpose. The central idea of a model is that
important relationships that apply to the system being modelled also apply to the model.
2. Models & Modelling Techniques
There are 7 types of DSS models with varying types of modelling techniques. These are:
Category Process and Objective Representative Techniques
1.Optimization of
Find the best solution from a small 1.Decision tables,
problems with
number of alternatives 2.Decision trees
few alternatives
1.Linear and other
Find the best solution from a large or an
2.Optimization mathematical program-
infinite number of alternatives using a
via algorithm ming models,
step by-step improvement process
2.Network models
3.Optimization
Find the best solution in one step using
via an analytic 1.Some inventory models
a formula
formula
Finding a good enough solution or the
4.Simulation best among the alternatives checked 1.Several types of simulation
using experimentation
Find a good enough solution
5.Heuristics 1.Heuristic programming,
using rules
1.Expert Systems Fore-
6.Predictive
Predict the future for a given scenario casting models,
models
2.Markov analysis
1.Financial modelling,
7.Other models Solve a what-if case using a formula
2.Waiting lines
DSS models are broadly classified into Static Models & Dynamic Models on which Static
Analysis & Dynamic Analysis is applied respectively.
3. Static Analysis
1. A Static model takes a single snapshot of situation.
2. In this static snapshot everything occurs in a single interval.
3. Static models do not explicitly take time into account.
4. An example is of a make or buy decision. Also, an annual accounting statement or
financial statement is also an example of static model. Though the financial statements
& activities adhere to an accounting period, the time frame is fixed hence it is static.
5. Stability of the relevant data is assumed.
6. Certainty Analysis:
1. Complete knowledge is available.
2. Decision maker knows the outcome of each course of action.
3. Situation involved is often with structured problems with short time horizons.
4. Certain models are relatively easy to develop and solve and they can yield optimal
solutions.
7. Uncertainty Analysis:
1. There are several outcomes for each course of action.
2. Decision maker does not know, or cannot estimate the possible outcomes.
3. This type of analysis is more difficult because of insufficient information. It involves
assessment of the decision maker’s attitude towards risk.
8. Risk Analysis:
1. Decision maker must consider several possible outcomes for each alternative.
2. The decision maker can assess the degree of risk associated with each alternative.
3. Risk analysis can be performed by calculating the expected value for each alternative
and selecting the one with best expected value.
9. Decision analysis is used with decision tables and decision trees. Single-goal situations can
be modelled with decision tables or decision trees.
1. Decision tables are used to organize information and knowledge in systematic tabular
manner.
2. Decision Trees are an alternative representation of the decision table. They show the
relationship of the problem graphically and handle complex situation. Decision Trees
can be cumbersome if there are many alternatives or static nature.
3. Components of decision support mathematical models:
• Result Variables: These reflect the level of effectiveness of a system.
• Decision Variables: These describe alternative course of action.
• Uncontrollable Variables: These represent some factors that affect the result
variables but not under the control of decision maker.
• Intermediate result Variables: These reflect the intermediate outcomes in
mathematical models.
11. What-If-Analysis addresses the context of what will happen to the solution if an input
variable, an assumption, or a parameter value is changed. With the appropriate user
interface, it is easy for manager to ask a computer model different questions and get the
answers. This analysis is common in expert systems. Through this the user gets an
opportunity to change their answers to some questions.
12. Goal Analysis is used to calculates the values of the inputs necessary to achieve a desired
level of output. It represents a backward solution approach since the objective is defined.
13. Problem solving search methods: The choice phase of problem solving involves a search
for an appropriate course of action. Search approaches are:
1. Analytical Techniques
2. Algorithms
3. Blind Searching
4. Heuristic Searching
15. Probabilistic Simulation: It is used when there are one or more of the independent
variables. It follows certain probability distributions namely:
1. Discrete distribution
2. Continuous distribution
3. It is conducted with the aid of technique called Monte Carlo simulation.
17. Visual Simulation: It is used in graphical display of computerized results & includes
animations. It is one of the most successful development in computer-human interactions
and problem solving.
3. Data mining
Data Mining (DM) is a term used to describe knowledge discovery in databases. Data mining
is a process that uses statistical, mathematical, artificial intelligence and machine-learning
techniques to extract and identify useful information and subsequent knowledge from large
databases.
Data mining is a process that aims to use existing data to invent new facts and to uncover new
relationships. The objectives & characteristics of data mining are:
1.1.Traditional Approach:
Also known as the Waterfall model for development the traditional approach of DSS
development contains 4 steps and is as follows.:
a. Planning: The needs or problems & opportunities of a business are identified. All
possible requirements of the system to be
developed are captured in this phase and
documented. If required a feasibility study is
conducted pertaining to cost, financial,
technical & organizational feasibility. Once
the project is approved, a project manager is
assigned, who creates a work plan, staffs the
project, and adopts methods for managing it.
b. Analysis: In this phase important inputs are
addressed, such as intended users, objective
of the system & other intricacies. An
analysis is developed & if available an
existing system us analysed & a path
towards migration to new system is defined which leads more information gathering,
development of a process model & a data model.
c. Design: The requirement specifications from first phase are studied in this phase and
the system design is prepared. This system design helps in specifying hardware and
system requirements and helps in defining the overall system architecture.
d. Implementation: The implementation phase brings it all together. This is where the
system is built or purchased. Construction involves not only building the system. but
also testing it to verify that it works. Better planning can lead to systems with fewer
bugs. Installation is the last step and involves actually getting the system up and
running.
Alternative methodologies exist for developing a DSS like RAD (Rapid Application
Development) where a system is developed quickly and users can obtain some functionality as
soon as possible. These include methods of phased development, prototyping, and
throwaway proto typing. The phased development methodology involves breaking a system
up into a series of versions that are developed sequentially. Each version has more functionality
than the previous one, and they evolve into a final system. The advantage is that users gain
functionality quickly; the disadvantage is that the systems with which users start to work are
incomplete by design.
1.2.Prototyping
a. Prototyping involves performing the analysis, design, and implementation phases
concurrently and repeatedly. System prototypes are quickly developed and
demonstrated to users; whose input is used to refine them.
b. The main advantage is that systems are quickly provided to users even if not yet ready
for institutional use. Feedback is obtained, and the system can be modified on moving
to the next prototype. Further analysis may be needed as well.
c. One disadvantage is that changes are introduced quickly and there is no attempt to
correct design decisions early on. Instead they are repaired as the system evolves.
a. Identification: The knowledge engineer and expert determine the important features of the
problem. This includes identifying the problem itself (e.g. type and scope), the participants
in the development process (e.g. additional experts), the required resources (e.g. time and
computing facilities), and the goals or objectives of building the expert system (ex. improve
performance or distribute scarce expertise).
b. Conceptualization: The knowledge engineer and expert decide what concepts, relations
and control mechanisms are needed to describe problem solving in the domain. Subtasks,
strategies and constraints related to the problem-solving activity are also explored. At this
time the issue of granularity is addressed. This means considering the level of detail of
represented knowledge. The knowledge engineer normally picks the most abstract level of
detail (coarsest grain) that still provides adequate discrimination between key concepts.
The developers must avoid trying to produce a complete problem analysis before beginning
program implementation, since much learning comes from the 1st implementation that
shapes and directs the conceptualization process.
c. Formalization: Formalization involves expressing the key concepts and relations in some
formal way, usually within a framework suggested by an expert system building language.
Thus, the knowledge engineer should have some ideas about appropriate tools for the
problem by the time formalization begins.
d. Implementation: The knowledge engineer turns the formalized knowledge into a working
computer program. Constructing a program requires content, form and integration. The
content comes from the domain knowledge made explicit during formalization i.e. the data
structures, inference rules and control strategies necessary for problem solving. The form
is specified by the language chosen for system development. Integration involves
combining and reorganizing various pieces of knowledge to eliminate global mismatches
between data structures and rule or control specifications. Implementation must be rapidly
as the rationale for implementing the initial prototype is to check the effectiveness of the
design decisions made during the earlier phases of development. This means that there is a
high probability that the initial code will be revised or discarded during development.
e. Testing: Testing involves evaluating the performance and utility of the prototype program
and revising it as necessary. The domain expert typically evaluates the prototype and helps
the knowledge engineer to revise it. As soon as the prototype runs on a few examples, it
should be tested on. many problems to evaluate its performance and utility. This evaluation
may uncover problems with the representational scheme, such as missing concepts and
relations, knowledge represented at the wrong level of detail, or unwieldy control
mechanisms. Such problems may force the developers to recycle through the various
development phases, reformulating the concepts, refining the inference rules and revising
the control flow.