Atal Bihari Vajpayee Indian Institute of

Information Technology and Management,

Gwalior

Assignment 3
Decision Support and Expert System

Submitted to:
Dr. Vinay Singh

Submitted by:
Rahul Dev
 2018IMG-043
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Question 1:

To model a decision support system, please answer the following:

a) How to identify a problem for decision support system design?

The first phase, known as the intelligence phase, entails assessing corporate priorities and strategies
relevant to a problem and deciding whether or not they are being followed. Dissatisfaction with the
status quo leads to problems. The word "problem recognition" refers to the process of determining
the cause of frustration, its manifestations, the magnitude of the problem, and its clear definition.
Frequently, what is referred to as a problem is just a symptom of a larger issue.

This is a common occurrence in real-world problems due to the interconnected nature of the issues.
Monitoring and assessing the organization's efficiency level will reveal the presence of a challenge.
Data processing on efficiency and forecasting future data are two of the most difficult measures in
data analysis. It is possible to assess whether an issue occurs, where it is located, and how serious it
is until the formal examination is finished. The biggest question is whether an information system
reports a problem or just the signs of a problem.

The business intelligence tools or decision support systems aid decision making in an organization.
An effective DSS provides you with unbiased data analysis, real time monitoring and rich reporting,
supporting you to make an informed decision in the least possible time span. A meticulously
designed DSS makes use of analytical models, various statistical and econometric tools and of
course, human intelligence and insights to support decision making.

This proves the importance of technology, methodology and approach behind designing and
development of a decision support system. As a decision maker, you need to be extremely careful in
selecting the DSS technology and developmental methodology. You need to get the basics right, in
order to get a reliable tool to support diverse information and decision-making needs.
Because designing and development of a decision support system is a complex process, you may face
a number of issues, such as:
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

1. Mismatch between the perspectives of the programmer and decision maker

Decision makers, on one hand, have very little knowledge about what it takes to design and
develop a decision support system. On the other hand, a programmer or developer may not
have a fair idea of how complex business decision making has become in today’s highly
turbulent times. Technology selection may seem puzzling and ambiguous to decision maker
while the preferences, needs and expectations of a decision maker may not fit the process of
system design and development. This mismatch between perspectives leads to complexities.
But at the same time, this increases the likelihood of creation of an effective and apt DSS.

2. Identification of specific requirements

Most of the time, even decision makers have no clue about what to expect from a decision
support system. This is especially the case when managers need a tool to aid in resolving ill-
structured or unstructured problems. It is easy to decide what functionality a DSS must
possess when problems are routine and structured. Managers can seek help from their team
members and conduct brainstorming sessions, in order to chart out the functions and benefits
of a decision support system.

3. Technology selection
In today’s highly competitive business environment, you need an interactive and responsive
decision support system that maximizes your performance. In such a scenario, the selection of
technology plays a crucial role. However, it’s not always necessary to use the latest version of
a particular platform. It completely depends on the objectives you wish to achieve. However, a
DSS development company may push you for the latest technology, which will certainly add
to your expenses. The rule of thumb is to ask for price quotes from different companies.

4. Approach to software design and development

As said earlier, there is no standard approach or methodology to design the best decision
support system. There are three main approaches to system design and development: 1) the
traditional system development life cycle (SDLC) approach; 2) rapid prototyping and 3) end-
user approach. You may want to choose a methodology that ensures that the final product
accomplishes your objectives. But each approach has its pros and cons, making it difficult to
choose the best one.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

b) How the analysis of the environment is done where

decision options are operational?

Environmental scanning and interpretation are one of the most important facets of issue assessment.
Monitoring, scanning, and interpreting gathered data are also part of environmental scanning. Since
no decision is taken in a vacuum, there are several factors to weigh. The scale of the domain, as well
as the forces and complexities of the system, must all be considered. The degree of centralization, as
well as the organisational culture and corporate decision-making processes, must all be identified.
Environmental conditions may have contributed to the current dilemma in an environment where
decision alternatives are operational. By searching for problems, business intelligence or business
analytics software may assist in identifying the issue.

One very important aspect is environmental scanning and analysis, which is the monitoring,
scanning, and interpretation of collected information. No decision is made in a vacuum. It is
important to analyze the scope of the domain and the forces and dynamics of the environment. One
should identify the organizational culture and the corporate decision-making processes (who makes
decisions, degree of centralization, and so on). It is entirely possible that environmental factors have
created the current problem.

Business intelligence (business analytics) tools can help identify problems by scanning for them (see
Hall, 2002a, 2000b; Whiting, 2003; the MSS Running Case in DSS in Action 2.6; and DSS in Action
3.6, where we describe how NetFlix.com creates usable environmental information for
moviegoers). The problem must be understood, and everyone involved should share the same frame
of understanding because the problem will ultimately be represented by the model in one form or
another (as was done in the opening vignette). Otherwise, the model will not help the decision-
maker.

The issue must be comprehended. Since the dilemma would inevitably be expressed by the model in
some way or another, everyone concerned should have the same frame of mind. The model would
not assist the decision-maker if this is not the case. The decision variables in the model, as well as
their relationships, must be identified. In this method, influence diagrams and schematic
representations of mathematical models may be useful. A cognitive map may also aid in the
development of a decision-maker's understanding of the problem, especially variables and
interactions.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

c) Justify the fact that “there may be need of multiple models”

in DSS design.
The aim of management decision analysis is to determine how fast each option moves management
closer to its goal. Unfortunately, management issues are rarely assessed with a single objective in
mind. Management schemes are much more difficult to understand. Similar owners have various
objectives. Managers want to achieve these many objectives, some of which could be incompatible.
It is often important to evaluate each option in terms of its impact on each of many objectives.
Multiple models could be needed to make this practical.

A decision support system can include several models (sometimes dozens), each of which represents
a different part of the decision-making problem. For example, the Procter & Gamble supply chain
DSS includes a location model to locate distribution centers, a product-strategy model, a demand
forecasting model, a cost generation model, a financial and risk simulation model, and even a GIS
model. Some of the models are standard and built into DSS development generators and tools. Others
are standard but are not available as built-in functions. Instead, they are available as freestanding
software that can interface with a DSS. Nonstandard models must be constructed from scratch. The
P&G models were integrated by the DSS, and the problem had multiple goals. Even though cost
minimization was the stated goal, there were other goals, as is shown by the way the managers took
political and other criteria into consideration when examining solutions before making a final
decision. Sodhi and Aichlmayr (2001) indicate how Web-based tools can be readily applied to
integrating and accessing supply chain models for true supply chain optimization. Also see DSS in
Action 4.1 for how United Airlines is integrating its models into a major DSS tool.

Most of these issues can be resolved by:

• Identifying clear agendas

• Brainstorming with team members

• Communicating the expectations clearly to the programmers

• Educating yourself about various technologies used in DSS development

 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

d) What are the sufficient bases to categorize different DSS models.

DSS models can be classified into seven groups. The categories of DSS, along with their
representative techniques, are shown in Table 1.
Table 1: Categories of Models

Category Process and Objective Representative Technique

Optimization of problems with Find the best solution from a Decision trees, decision tables
few alternatives small number of alternatives
Optimization via algorithm Find the best solution from a Linear and other mathematical
large or an infinite number of programming models, network
alternatives using a step-by-step models
improvement process
Optimization via an analytic Find the best solution in one Some inventory models
formula step using a formula
Simulation Finding a good enough solution Several types of simulation
orthebestamongthe
alternatives checked using
experimentation

Heuristics Find a good enough solution Heuristic programming, expert

using rules systems

Predictive models Predict the future for a given Forecasting models, Markov
scenario analysis

Other models Solve a what-if case using Financial modeling, waiting

formula lines

Each technique can be applied to either a static or a dynamic model, which can be constructed under
the assumed environment of certainty, uncertainty, or risk. Special decision analysis systems with
modeling languages and capabilities embedded in them can expedite model construction.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

We have already seen the classification of decision support systems on the basis of technologies used
in the history section. Let’s now look at the categorization on the basis of nature of operations:

1. File Drawer System: As the name suggests, a file drawer decision support system provides
information useful for making a specific decision. It works like a file drawer where different
types of information are stored under different names or categories.

2. Data Analysis Systems: These decision support systems are based on a formula; and
therefore, are used to make comparative analysis. These make use of simple data processing
tools, such as inventory analysis.

3. Information Analysis System: This kind of decision support system analyzes different sets of
data to generate informational reports that can be used to assess a situation for decision
making.

4. Accounting and Financial Support System: This type of support system is based on to keep
track of cash and inventory.

5. Representation or Solver Model: This type of system performs or represents decision

making in a particular domain or for a specific problem. It calculates and compares the
outcomes of different decision paths. The decision maker can conduct a ‘what if’ analysis and
make an informed decision basis on the outcomes generated.

6. Optimization Model: This DSS is based on stimulated models, majorly providing guidelines
for operations management. The focus is on providing optimal solutions on job scheduling,
product mix and material mix decisions.

7. Suggestion System: This type of support system suggests optimal decision for a particular
situation by assisting in collecting and structuring data.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Categorization of DSS on the Basis of Inputs

• Text-Oriented DSS

• Database Oriented

• Spreadsheet Oriented

• Rule Oriented

• Solver (specific situation) Oriented

• Compound/Hybrid: This support system combines two or more structures from above to offer
multiple functionalities.

Categorization of DSS on the Basis of Support Offered

• Personal DSS

• Group DSS

• Organizational DSS

Categorization of DSS on the Basis of Type and Frequency of Decision Making

• Institutional DSS: An institutional decision support system supports recurring decisions on an

ongoing basis. Basically, this is for programmed decisions, which are made on a daily basis.
For example, establishing routine for handling technical problems, taking disciplinary actions,
unit manufacturing, a mechanic process of troubleshooting, etc.

• Ad-hoc DSS: An ad-hoc decision support system supports one kind of decision in an
unanticipated situation. The decision made is unique to a problem. This type of system is used
to support non-programmed decisions as the information available is incomplete.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

e) Write notes on DSS model management.

Models are a key component in most decision-making processes. Systems developed to effectively
support the decision-making process must accommodate the models that give focus to the decision-
making motifs of the individual decision maker. The model management process is examined and the
objectives of such a system for computer-aided support of model management is described.
Alternative forms of knowledge representation in model representation are considered. Abstractions
are singled as a robust model representation form. The model management system must facilitate the
definition and maintenance of models and data as a resource in decision-making support. A prototype
Decision Support System to support model management involving econometric modeling in the
planning process is briefly described. The prototype system incorporates reference and user databases
containing time-series data, model database of equations, a global directory to facilitate distribution
and control, and a control program providing a flexible user interface.

A model management system is a software package that includes financial, statistical, management
science, or other quantitative models that provide the systems’ analytical capabilities and appropriate
software management. It also includes modeling languages for building custom models. Hence, the
subsystem is also called the model base management subsystem (MBMS). A model management
system of DSS is composed of the following elements – a model base, model base management
system, modeling language, model directory, and model execution, integration, and command
processor. An effective MBMS makes the structural and algorithmic aspects of the model
organization and associated data processing transparent to the users. Some of the desirable
capabilities of MBMS are:

Control

Flexibility

Feedback

Interface

Redundancy reduction

Increased consistency

An MBMS allows its users to:


Access and retrieve existing models

Exercise and manipulate existing models

Store existing models
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Q2. Write notes on the following:

a) Mathematical models

MSS mathematical models refer to models relating to mathematics, finance, or engineering. The
different components of mathematical models are:


Decision variables – They describe the alternative courses of action. The decision-makers
control these variables. These variables may change according to the problem at hand.


Uncontrollable variables – They are the factors that affect the result variables but are not
under the decision-maker’s control. These factors can be fixed (parameters), or they can vary
(variables). Most of the factors are uncontrollable because they are in and determined by
elements of the system environment. Some of these variables limit the decision-maker and
hence act as constraints of the problem.


Result variables – They reflect intermediate as well as the outcome. They reflect the level of
effectiveness of the system, i.e., they indicate how well the system performs or attains its
goal(s). Result variables are called dependent variables. Intermediate result variables are
sometimes used in modeling to identify intermediate outcomes. Result variables depend on
the occurrence of the decision and the uncontrollable independent variables.

The result of the decision s determined by the decision made (value of decision variables), the factors
that cannot be controlled by the decision-maker (in the environment), and the relationships among
the variables.

The modeling process involves identifying the variables and relationships among them.
The components of a quantitative model are linked together by mathematical expressions – equations
or inequalities.

All models are made up of three basic components: decision variables, uncontrollable variables (and/
or parameters), and result (outcome) variables.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Mathematical relationships link these components together. In nonquantitative models, the

relationships are symbolic or qualitative. The results of decisions are determined by the decision
made (value of the decision variables), the factors that cannot be controlled by the decision-maker (in
the environment), and the relationships among the variables. The modeling process involves
identifying the variables and relationships among them. Solving a model determines the values of
these and the result variable(s).

THE STRUCTURE OF MSS MATHEMATICAL MODELS

The components of a quantitative model are linked together by mathematical (algebraic) expressions
—equations or inequalities. A very simple financial model
is P = R - C, where
P = profit
R = revenue
C = cost.
The equation describes the relationship among these variables. Another well-known financial model
is the simple present-value cash flow model,

P= V/(1+i)^n

where P = present value, F = a future single payment in dollars, i = interest rate (percentage), and n =
number of years.
With this model, one can readily determine the present value of a payment of $100,000 to be made
five years from today, at a 10 percent (0.1) interest rate, will be-:
100,000/(1+0.1)^5
= $62,092
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

b) Mathematical Model Optimization

Optimization requires a decision-maker to consider the impact of each alternative course of action on
the entire organization because the decision made in one area may have significant effects, positive
or negative, in other areas. A systems point of view assesses the impact of all decisions on the entire
system. Suppose a suboptimal decision is made in one part of the organization without considering
the organization’s details. In that case, an optimal solution from the point of view may be inferior for
the whole. Linear programming (LP) is the best-known technique in a family of optimization tools
called mathematical programming. Mathematical optimization help to solve managerial problems in
which the decision-maker must allocate the scarce resources among competing activities to optimize
a measurable goal. Mathematical problems typically have a large number of possible solutions.
Depending on the underlying assumptions, the number of solutions can be either infinite or finite. Of
the available solutions, at least one is the best, in the sense that the degree of goal attainment
associated with it is the highest. This solution, where the total reward is maximized, is called the
optimal solution.

The most common optimization problems in the field of mathematical modeling are:


Dynamic programming


Goal programming


Linear and integer programming


Simple inventory models


Transportation
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

c) Programming of Mathematical Model Optimization

Mathematical programming is a family of tools designed to help solve managerial problems. The
decision-maker must allocate the scarce resources among competing activities to optimize a
measurable goal. Linear programming (LP) is the best-known technique in a family of optimization
tools called mathematical programming. Every LP problem is composed of:


Decision variables – Variables whose values are unknown and to be searched for.


Objective function – A linear mathematical function that relates the decision variables to the
goal, measure’s goal attainment, and is optimized.


Objective function coefficients – Unit profit or cost coefficients indicating the contribution to
the objective of one unit of a decision variable.


Constraints – They are expressed in linear inequalities or equalities that limit resources and/
or requirements. These relate the variables through linear relationships.


Capacities – They describe the upper and lower limits on the constraints and variables.


Input-output coefficients – They indicate resource utilization for a decision variable.

Some of the assumptions on which the programming of mathematical model optimization are based
are:


Returns from different allocations can be compared.

The return from any allocation is independent of other allocations.

The total return is the sum of the returns yielded by the different activities.

All data are known with certainty.

The resources are to be used most economically.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

d) Heuristics programming, its advantages, and limitation

Heuristics are decision rules governing how a problem should be solved. Heuristics are developed
based on a solid, rigorous analysis of the problem, which sometimes involves carefully designed
experiments. The heuristic process can be described as developing rules to help solve complex
problems or intermediate subproblems, finding ways to retrieve and interpret information on the fly,
and then developing methods that lead to a computational algorithm or general solution. Heuristic
programming uses heuristics to arrive at a feasible and “good enough” solution to complex problems.
Heuristics can either be quantitative or qualitative. Heuristic programming involves searching,
learning, evaluating, judging, and then re-searching, relearning, and reappraising as exploring and
probing takes place.


Tabu search heuristics – It is based on intelligent search strategies to reduce the search for
high-quality solutions in computer problem-solving. The method remembers the high-quality
and low-quality solutions it has found and tries to move toward other high-quality solutions
away from low-quality ones.


Genetic algorithms – They start with randomly generated solutions and recombine pairs of
them at random to produce offspring. Only the best offsprings and parents are kept to
produce the next generation. Random mutations may also be introduced.

Advantages of heuristics programming are:


Simple to understand, and hence easier to implement and explain.


Help train people to be creative and develop heuristics for other problems.


Saves formulation time.


Saves computer programming and storage requirements.


Often produce multiple acceptable solutions.


Save computational time, and hence real-time in decision making.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Limitations of heuristics programming are:


An optimal solution can’t be guaranteed. Sometimes the bound on objective values is
terrible.


There may be too many exceptions to the rules.


Sequential decision choices may fail to anticipate the future consequences of each choice.


The interdependencies of one part of a system can sometimes have a profound influence on
the whole system.

The determination of optimal solutions to some complex decision problems could involve a
prohibitive amount of time and cost or may even be impossible. Alternatively, the simulation
approach may be lengthy, complex, inappropriate, and even inaccurate. Under these conditions it is
sometimes possible to obtain satisfactory solutions more quickly and less expensively by using
heuristics.

Heuristic searches (or programming) are step-by-step procedures (like algorithms) that are repeated
until a satisfactory solution is found (unlike algorithms). In practice, such a search is much faster and
cheaper than a blind search, and the solutions can be very close to the best ones. In fact, problems
that theoretically can be solved to optimality (but with a very
long solution time) are in practice sometimes solved by heuristics, which can guarantee a solution
within a few percent of the optimal objective value.

Heuristic programming is the approach of using heuristics to arrive at feasible and "good enough"
solutions to some complex problems. Good enough is usually in the range of 90-99.9 percent of the
objective value of an optimal solution. Heuristics can be quantitative, and so can play a major role in
the DSS model base, where heuristics were used to solve a complex integer programming problem.
They can also be qualitative, and then can play a major role in providing knowledge to expert
systems.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

e) Simulation-based modeling, advantages, and limitations

Simulation is a technique of conducting experiments with a computer on a model of the management

system. Simulation is a technique for controlling experiments. It involves testing specific values of
the decision or uncontrollable variables in the model and observing the impact on the output
variables. Simulation is a descriptive rather than a normative method. It helps to represent the semi-
structured and unstructured situations. A simulation model describes or predicts the characteristics of
a given system under different conditions. A simulation process usually repeats an experiment
several times to estimate the overall effect of specific actions. The process is used when a problem is
too complex to be treated by numerical optimization techniques. Complexity means either that
the problem cannot be formulated for optimization, the problem is too significant, there are too many
interactions among the variables, or the problem is stochastic.

Advantages of simulation are:


A significant amount of time compression can be attained, quickly giving the manager some
feel about the long-term effects of many policies.

Simulation allows the manager to pose what-if questions. Managers can use a trial-and-error
approach to problem-solving and can do so faster, cheaper, and more accurately, with less
risk.

The manager can experiment to determine which decision variables and which parts of the
environment are essential and with different alternatives.

The model is built from the manager’s perspective.

Simulation is often the only decision modeling method that can readily handle relatively
unstructured problems.

Limitations of simulations are:


An optimal solution cannot be guaranteed, but relatively good ones are generally found.

Simulation model construction can be a slow and costly process, although newer modeling
systems are easier to use.

Solutions and inferences from a simulation study are usually not transferrable to other
problems because the model incorporates unique problem factors.

Simulation is sometimes so easy to explain to managers that analytic methods are often
overlooked.

Simulation software sometimes requires special skills because of the complexity of the
formal solution method.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Q3. Please refer the case application 4.1: “Clay Process Planning
at Imerys: A Classical case of Decision Making” (attached as
Annexure-I). Answer the following:

(a) What is the POP DSS used for?

POP model is a large-scale, generalized, multicommodity network flow model with side constraints.
In DSS, the POP model is used when dealing with multiple decision variables. It helps to optimize
the cost function, keeping in mind the constraints on the decision variables and the constraints on
environmental factors.

(b) What are the benefits of using a network-based model?

A network-based model helps inefficient representation of data, especially where multiple
commodities are involved. The multicommodity network flow model represents the network flow
problem of many commodities through standard links that generally have capacity limits. The model
can be represented graphically, making it easy to sketch and understand. An additional advantage of
the model is that each link that carries a flow can multiply between 0 and 1, indicating how much
flow reaches the node at the end of the link. This can be used to model losses between two nodes.
Multiple processes can be represented using the same structured block, which makes the model easy
to understand.

(c) What are the benefits of the POP DSS?

The benefits of POP DSS are as follows:


It provides the user with a friendly interface, using which the user can set demands and adjust
to the processes. The POP DSS then returns the data after accessing the database and
provides the user with the managerially meaning graphs.

For a fixed time, the model returns which nodes are active, along with their performance. It
also suggests that the changes to nodes increase their efficiency and capacity to be better
utilized.

In case of a node failure, the model automatically computes what counter-measures should be
taken to minimize losses.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

(d) How can what-if cases (scenarios) be used to determine whether

to add extra processing equipment instead of adjusting existing
processes and chemical use?

The model automatically computes the efficiency and utilization factor of mines and plants. Using
the what-if cases can determine if the plants and mines are being utilized at their maximum capacity.
These what-if cases can now be used to judge if the mines and plants are operating in optimal
conditions or not. If the conditions are not optimal, then the existing process and chemical use can be
adjusted. Else extra processing equipment needs to be added.

(e) Could other firms that process materials use a system like
this? Why or why not?

Yes, other firms that process materials can use a system like this—taking an example of an industry
that processes plastics. The situation is similar to that of the example taken. The plastic industry also
depends on a variety of minerals, thus involving the use of various mines. Different composition of
these minerals produces different plastics varieties, which is analogous to the varieties of clays
produced in the example.

(f) How could a demand forecasting model be integrated with

POP? (A question to think about-not in this case application.)

In the POP model, all the entities are denoted through similar nodes. Nodes demote even entities like
source (e.g. mines, supply) and sink (e.g. demand of final product). The demand forecasting model
can be integrated as a feedback mechanism between the sink and the nodes involved in clay
production. The model can now predict the demand for specific products on the market. Using this as
feedback, the production process can be altered to give attention to certain products that are more in
demand and produce higher profits.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

(g) How could the results of the POP DSS guide an enterprise
resource planning (ERP) system? (A question to think about-
not described in this case application.)

Enterprise resource planning (ERP) systems are complete, integrated systems that manage all aspects
of a production-based or distribution business, aligning financial management, human resources,
supply chain management, and manufacturing or distribution with the core function of accounting.
ERP systems are used to provide transparency into the entire business process by tracking all aspects
of production or distribution, financials, and back office.
As discussed in the previous question, a POP model integrated with demand forecasting can be
integrated with an ERP system. The demand forecasting models and POP model results can together
act as an input to the ERP system, which may help to plan to increase the production of certain
products.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Q4. How and in what circumstances the Business Intelligence: Data

Warehousing, Data Acquisition, Data Mining, Business Analytics,
and Visualization are used in Decision Support System.

Many organizations use a vast amount of data to survive in the competing world. Managers need this
data to help them make profitable decisions for their firm. Foundational data architecture and
enterprise architecture must be in place to facilitate practical decision analysis. These architectures
help the managers to use analytic tools to improve organizational decision-making with the help of
DSS. Enabling decision-making through access to all relevant information is known as business
intelligence. Business intelligence includes data warehousing, online analytical processing, data
mining, and visualization, and multidimensionality.

i. Data warehousing – The data required by the organizations are scattered across many
government agencies, and consolidating the data to make them available when needed entails
severe organizational and technical challenges. Data warehousing helps a DSS by supporting
decision-making, analyzing large amounts of data from various sources to provide rapid
results to support a critical process. Data for the data warehouse are brought in from various
external and internal resources and are cleansed and organized according to the organization’s
needs. The knowledge base management subsystem of DSS uses this data for processing, and
passes them onto to build models. DSS can also use the data to present them to the user in
raw form or graphical representation.

Some of the characteristics of data warehousing are:


Subject-oriented


Integrated


Time-variant


Nonvolatile


Summarized


Not normalized
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

ii. Data acquisition – The need to extract data from many internal and external sources
complicated the task of DSS building. Regardless of how the data is collected, data must be
validated and filtered. To collect data for DSS, raw data can be collected manually or by
instruments and sensors. Representative data can be collected using time studies, surveys,
observations, and soliciting information from experts. The most reliable way of data
acquisition is from point-of-purchase inventory control. The data collected for the use of DSS
should be reliable and accurate. Data quality (DQ) is a critical issue because quality
determines the usefulness of data and the decisions’ quality.

iii. Data mining – Data mining (DM) is the term used to describe knowledge discovery in
databases. It 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 used in situations where the relationship
among different system variables is unknown or cannot be expressed mathematically. Data
mining includes knowledge extraction, data archeology, data exploration, data pattern
processing, data dredging, and information harvesting. Data mining works closely with the
knowledge-based management system of the DSS, where it provides intelligence to the
decision-makers. Effectively leveraging data mining tools and technologies can lead to
acquiring and maintaining a strategic competitive advantage. Data mining offers
organizations an indispensable decision-enhancing environment to exploit new opportunities
by transforming data into a strategic weapon. Data mining can solve different classes of
problems. These classes are:

Classification


Clustering


Association


Sequencing


Regression


Forecasting
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

iv. Business analytics – Business intelligence involves acquiring data and information from
various sources and utilizing them in decision-making. Business analytics adds dimension to
business intelligence: models and solution methods. Business analytics provides charts and
graphs of multidimensional data using specific methods. These methods generally access data
from data warehouses and deposit them into a local, multidimensional database system.
Business analysis is used in DSS in the following ways:


It analyzes the underlying strategic and tactical business goals and objectives that
drive the development of the solution.


It analyzes the existing business and technical organizational structures, the
organization’s culture and leadership style, whether the roles and responsibilities have
been established, and whether people with an appropriate amount of time and skills
are in place.


It analyzes whether the appropriate technical infrastructure and development
methodologies are in place.

v. Visualization – Data visualization refers to technologies that support visualization and

sometimes interpret data and information at several points along the data processing chain.
Visual tools can help identify relationships directly. The ability to identify significant trends
in corporate and market data provides enormous advantages. More accurate predictive models
provide significant business advantages in applications that drive content, transactions, or
processes. Data visualization enables OLAP and data mining to utilize Web-based tools. It
offers users capabilities for self-guided exploration and visual analysis of large amounts of
data.
 Assignment 3 | Rahul Dev | 2018IMG-043 | IPG-MBA 2018

Q5. Develop and present an IT-driven generic model of a Decision

Support System.

A. The sustainable development of an increasingly service-based economy requires efficient

allocation to the various existing user classes of non-storable service infrastructures. That decision is
often taken in phases. Similarly, some strategic decisions have to be made. In a second decision
stage, operational decisions will be taken. To accomplish the organization’s tasks, the model uses
optimization heuristics, whose relative effectiveness depends strongly on the characteristics of the
demand.
There are three main components in a DSS: database, model base, and software system. The software
system, in turn, is composed of three components: the DBMS (Database Management Software),
which in conjunction with the database constitutes the data subsystem; the MBMS (Model Base
Management Software), which in conjunction with the model base constitutes the model subsystem;
and the dialog generation and management software which forms the system user interface. The
model subsystem is within the scope of a DSS, what is frequently referred to as a Model
Management System (MMS), which can be defined with a comprehensive agreement as “a software
system that facilitates the development, storage, manipulation, control, and effective utilization of
models in an organization.”