DSS Chapter ONE
DSS Chapter ONE
1.1. Introduction
Today, at the turn of the 21st century, many managers are using computers,
business databases, and models to help make decisions. This is a positive change
in behavior, and some evidence indicates the use of computers to support
management decision making is entering a new and more sophisticated stage. The
novelty of managers using computers is wearing off, and, more importantly, the
capabilities of our support systems are beginning to match the expectations of
managers. Decision Support Systems (DSS) are now both a business necessity
and an opportunity to gain competitive advantage. This chapter tries to build on
these positive changes and provide an overview of computerised decision support
systems.
Typical information that a decision support application might gather and present
would be:
(i) An inventory of all of your current information assets (including legacy and
relational data sources, cubes, data warehouses, and data marts).
(ii) Comparative sales figures between one week and the next.
(iii) Projected revenue figures based on new product sales assumptions.
(iv) The consequences of different decision alternatives, given past experience
in a context that is described.
1
(b) A DSS is a computer program application that analyses business data and
presents it so that users can make business decisions more easily. It is an
“informational application” and is different from an “operational
application” that collects the data in the course of normal business
operation. A DSS may present information graphically and may include an
expert system or artificial intelligence (AI). It may be aimed at business
executives or some other group of knowledge workers.
(d) A DSS is an umbrella term used to describe any computer application that
enhances the user’s ability to make decisions. More specifically, the term is
usually used to describe a computer-based system designed to help
decision-makers use data, knowledge and communications technology to
identify problems and make decisions to solve those problems.
2
improves, completes, and refines the suggestions of the decision maker and
sends them back to him/her for validation. The whole process then starts
again, until a consolidated solution is generated.
(b) Data-Driven DSS – are a form of support system that focuses on the
provision of internal (and sometimes external) data to aid decision making.
Most often this will come in the form of a data warehouse – a database
designed to store data in such a way as to allow for its querying and analysis
by users. Data-driven DSS emphasises analysis of large amounts of structured
data. These systems include: real-time equipment monitoring, inventory
reorder, and monitoring systems.
While data-driven DSSs rely on data that is already in a standardised format that
lends itself to database storage and analysis, a document-driven DSS makes use
3
of data that cannot easily be standardised and stored. The three primary forms of
data used in document-driven DSSs are:
(i) Oral – i.e. transcribed conversations;
(ii) Written – i.e. reports, memos, e-mail and other correspondence;
(iii) Video – i.e. TV commercials and news reports.
None of these formats lend themselves easily to standardised database storage and
analysis, so managers require DSS tools to convert them into data that can be
valuable in the decision making process. Document-driven DSS is the newest
field of study in Decision Support Systems. Examples of document-driven tools
can be found in internet search engines, designed to sift through vast volumes of
unsorted data through the use of keyword searches
4
(f) Spreadsheet-based DSS – model-driven and data-driven DSSs can be built
using spreadsheets which offer decision-makers easy to understand
representations of large amounts of data. Additionally, spreadsheet data is
arranged in such a way as to make it easy to convert the data into
visualisations to further aid decision-makers.
(g) Web-based DSS – any type of DSS can be web-based. The term simply
describes any decision support system that is operated through the interface of
a web browser, even if the data used for decision support remains confined to
a legacy system such as a data warehouse.
5
Figure 1: DSS Architecture
6
Some of the commonly used models are as follows:-
(a) Statistical Models: They contain a wide range of statistical functions, such as
mean, median, mode, deviations etc. These models are used to establish,
relationships between the occurrences of an event and various factors related
to that event. It can, for example, relate sale of product to differences in area,
income, season, or other factors. In addition to statistical functions, they
contain software that can analyze series of data to project future outcomes.
(b) Sensitivity Analysis Models: These are used to provide answers to what-if
situations occurring frequently in an organization. During the analysis, the
value of one variable is changed repeatedly and resulting changes on other
variables are observed. The sale of product, for example, is affected by
different factors such as price, expenses on advertisements, number of sales
staff, productions etc. Using a sensitivity model, price of the product can be
changed (increased or decreased) repeatedly to ascertain the sensitivity of
different factors and their effect on sales volume. Excel spreadsheets is often
used for making such analysis.
(c) Optimisation Analysis Models: They are used to find optimum value for a
target variable under given circumstances. They are widely used for making
decisions related to optimum utilisation of resources in an organisation.
During optimisation analysis, the values for one or more variables are changed
repeatedly keeping in mind the specific constraints, until the best values for
target variable are found. They can, for example, determine the highest level
of production that can be achieved by varying job assignments to workers,
keeping in mind that some workers are skilled and their job assignment cannot
be changed. Linear programming techniques and Solver tool in Microsoft
excel are mostly used for making such analysis.
(d) Forecasting Models: They use various forecasting tools and techniques,
including the regression models, time series analysis, and market research
methods etc., to make statements about the future or to predict something in
advance. They provide information that helps in analyzing the business
conditions and making future plans. These systems are widely used for
forecasting sales.
(e) Backward Analysis Sensitivity Models: Also known as goal seeking
analysis, the technique followed in these models is just opposite to the
7
technique applied in sensitivity analysis models. In place of changing the
value of variable repeatedly to see how it affects other variables, goal seeking
analysis sets a target value for a variable and then repeatedly changes other
variables until the target value is achieved. To increase the production level by
40 percent using the backward sensitivity analysis, for example, first, the
target value for the production level can be set and then the required changes
to made in other factors, such as the amount of raw material, machinery and
tools, number of production staff, etc., to achieve the target production level.
1.4.5. User
The managers or their staff specialists to explore decision alternatives can use a
decision support system. Such end users can also develop decision support
system.