Lecture Four Modelling and Analysis

Download as docx, pdf, or txt
Download as docx, pdf, or txt
You are on page 1of 5

MODELLING AND ANALYSIS

Modeling is a key element in most DSS/business intelligence (also business analytics)


and a necessity in a model-based DSS. There are many classes of models, and there
are often many specialized techniques for solving each one.
Simulation is a common modeling approach, but there are several others. For
example, consider the optimization approach taken by Procter and Gamble (P&G) in
redesigning its distribution system (Web Chapter). P&G's DSS for its North America
supply chain redesign includes several models:
A generating model (based on an algorithm) to make transportation cost estimates.
This model is programmed directly in the DSS.
• A demand forecasting model (statistically based).
• A distribution center location model. This model uses aggregated data (a special
modeling technique) and is solved with a standard linear/integer optimization
package.
• A transportation model (specialization of a linear programming model) to
determine the best shipping from product sources to distribution centers (fed to it
from the previous model) and hence to customers. It is solved using commercial
software and is loosely integrated with the distribution location model. These two
problems are solved sequentially. The DSS must interface with commercial software
and integrate the models.
 A financial and risk simulation model that takes into consideration some
qualitative factors that require important human judgment.
• A geographic information system (effectively a graphical model of the data) for a
user interface.

Major Modeling Issues


Some major modeling issues include problem identification and environmental
analysis, variable identification, forecasting, the use of multiple models, model
categories (or appropriate selection), model management, and knowledge-based
modeling.
1. IDENTIFICATION OF THE PROBLEM AND ENVIRONMENTAL ANALYSIS
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 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.

2. VARIABLE IDENTIFICATION Identification of the model's variables (decision,


result, uncontrollable, etc.) is critical, as are their relationships. Influence
diagrams, which are graphical models of mathematical models, can facilitate this
process. A more general form of an influence diagram, a cognitive map, can help
a decision-maker to develop a better understanding of the problem, especially of
variables and their interactions.
 Graphical representations of a model
“Model of a model”
 A tool for visual communication
 Some influence diagram packages create and solve the mathematical
model
 Framework for expressing MSS model relationships
Rectangle = a decision variable
Circle = uncontrollable or intermediate variable
Oval = result (outcome) variable: intermediate or final
Variables are connected with arrows  indicates the direction
of influence (relationship)
3. FORECASTING Forecasting is essential for construction and manipulation of
models because when a decision is implemented, the results usually occur in the
future. DSS are typically designed to determine what will be, rather than as
traditional MIS, which report what is or what was There is no point in running a
what-if analysis (sensitivity) on the past because decisions made then have no
impact on the futureHamey (2003) describes how firms attempt to predict who
their best (i.e., most profitable) customers are and focus in on identifying
products and services that will appeal to them. Part of this effort involves
identifying lifelong customer profitability. These are important aspects of how
customer relationship management and revenue management systems work.
4. MULTIPLE MODELS 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.

5. MODEL MANAGEMENT Models, like data, must be managed to maintain their


integrity and thus their applicability. Such management is done with the aid of
model base management systems .KNOWLEDGE-BASE D MODELIN G DSS uses
mostly quantitative models, whereas expert systems use qualitative, knowledge-
based models in their applications. Some knowledge is necessary to construct
solvable (and therefore usable) models. We defer the description of knowledge
based models until later chapters.
CATEGORIES OF MODELS

You might also like