Decision Support System

Decision Support System

The concept of system decision support ( DSS for short English Decision Support System ) is very broad, because there are many approaches to decision-making and due to the wide range of fields in which it is taken. These support systems are of the OLAP or data mining type , which provide information and support to make a decision.

A DSS can take many different forms. In general, we can say that a DSS is a computer system used to support, rather than automate, the decision-making process. The decision is a choice between alternatives based on estimates of the values ​​of those alternatives. Decision support means helping people who work alone or in groups to gather intelligence, generate alternatives, and make decisions. Supporting the decision-making process involves supporting the estimation, evaluation and / or comparison of alternatives. In practice, references to DSS are often references to computer applications that perform a supporting function.

Summary

[ hide ]

• 1 Definitions
• 2 Brief history
• 3 Function and characteristics
• 4 Taxonomies
• 5 Architectures
  • 1 Development environments
• 6 Additional bibliography
• 7 External links

Definitions

The term decision support system has been used in many different ways and has been defined in different ways depending on the author’s point of view.

• In rather more specific terms, a DSS is “an interactive, flexible and adaptable computer-based information system, specially developed to support the solution of an unstructured management problem to improve decision-making. It uses data, provides an interface friendly and allows decision-making in the analysis of the situation.

Other intermediate definitions between the two previous ones would be:

• A DSS is a “set of model-based procedures for processing data and judgments to assist a manager in his decision-making
• A DSS “combines individual intellectual resources with the capabilities of a computer to improve the quality of decisions (they are an IT support for decision makers on semi-structured problems)”
• “Extensible system capable of ad-hocsupport of data analysis and decision modeling, oriented to future planning and used at irregular, unplanned intervals”
• DSS is “Interactive computer systems that help decision makers use data and models to solve unstructured problems” * Keensays it is impossible to give a precise definition including all facets of DSS as “there can be no definition of decision support systems , but only of decision support
• For Power,the term DSS can refer to many types of information systems that support decision-making. Humorously, he adds that as long as a computer system is not an ‘online transaction processing system’ (OLTP), someone will be tempted to call it

As you can see there is no universally accepted definition of what a DSS is .

Brief history

According to Keen, it has evolved from two main areas of research: theoretical studies of decision-making organization, done at the Carnegie Institute of Technology in the late 1950s and early 1960s, and technical work on systems. Interactive computing, mainly carried out at the Massachusetts Institute of Technology in the 1960s. The concept of DSS is considered to have become such a research space in the mid-1970s, before gaining in intensity during the 1980s. In the mid-to-late 1980s, executive information systems (EIS), group decision support systems (GDSS), and organizational decision support systems (ODSS) evolved from the individual user and the model-oriented DSS.From approximately 1990, theData Warehouses and Online Analytical Processing (OLAP) began to expand the scope of DSS. With the turn of the millennium, new web-based analytical applications were introduced.

Function and characteristics

The DSS are very useful tools in business intelligence ( Business Intelligence ), they allow data analysis of the different business variables to support the decision-making process of managers:

• It allows to extract and manipulate information in a flexible way.
• Help in Decision Making # Unscheduled decisions.
• It allows the user to interactively define what information they need and how to combine it.
• It usually includes simulation, modeling tools, etc.
• You can combine information from the internal transactional systems of the company with those of another external company.

Its main feature is the ability to multidimensional analysis (OLAP) that allows you to delve into the information to a high level of detail, analyze data from different perspectives, make projections of information to forecast what may happen in the future, trend analysis , prospective analysis, etc.

A DSS supports people who have to make decisions at any level of management, be they individuals or groups, both in semi-structured and unstructured situations, through the combination of human judgment and objective information:

• Supports various interdependent or sequential decisions.
• It offers assistance in all phases of the decision-making process – intelligence, design, selection, and implementation – as well as a variety of decision-making processes and styles.
• It is customizable by the user over time to deal with changing conditions.
• It generates learning, resulting in new demands and refinement of the application, which in turn results in additional learning.
• Generally uses quantitative models (standard or custom-made).
• Advanced DSSs are equipped with a knowledge management component that enables effective and efficient resolution of very complex problems.
• It can be implemented for use on the Web, in desktop environments or on mobile devices ( PDAs ).
• Allows easy execution of sensitivity analyzes.

Taxonomies

As with the definition, there is no universally accepted taxonomy for DSS. Different authors propose different classifications. Using the relationship with the user as a criterion, Haettenschwiler distinguishes between:

• PassiveDSS .- It is an aid system for the decision-making process, but it cannot carry out an explicit decision, suggestions or solutions.
• ActiveDSS .- You can carry out said decision, suggestions or solutions.
• CooperativeDSS .- Allows the decision maker (or his advisers) to modify, complete or refine the decision suggestions provided by the system, before sending them back to the system for validation. The new system improves, completes and refines the decision maker’s suggestions and sends them back to their state for validation. Then, the whole process starts again, until a consolidated solution is generated.

Using the assist mode as a criterion, Power distinguishes between:

• Model-driven DSS.- Emphasis is placed on the access and manipulation of a statistical, financial, optimization or simulation model. It uses data and parameters provided by users to assist decision makers in analyzing a situation, which is not necessarily data intensive. Dicodess is an example of a model-based open source DSS.
• DSS directed by communication.- They have support for several people who work on the same shared task. Examples include built-in tools like Microsoft NetMeeting or Microsoft Groove
• Data Driven DSS.- Also called data driven , they emphasize the access and manipulation of time series of internal company data and, sometimes, also of external data.
• DocumentDriven DSS .- Manage, retrieve and manipulate unstructured information in a variety of electronic formats.
• KnowledgeDriven DSS .- Provide accumulated experience in the form of facts, regulations, procedures, or similar specialized structures for problem solving.

Using scope as a criterion, Power suggests this other classification:

• DSS for the large company.- This DSS will be linked to a large data warehouse and will serve many company managers, directors and / or executives.
• Desktop DSS.- It is a small system that can run on the personal computer of a manager it serves (a single user).

Architectures

Again, different authors identify different components for a DSS. Sprague and Carlson

• The database management system.- Stores information from various sources, it may come from the data repositories of a traditional organization, from external sources (such as the Internet), or from staff (from ideas and experiences of individual users).
• The model management system.- It deals with the representations of events, facts or situations using various types of models (two examples would be optimization models and search-target models).
• The manager system and generator of dialogues.- This is the user interface; It is, of course, the component that allows a user to interact with the system.

According to Power, a DSS has four fundamental components:

• The user interface.
• The database.
• Analytical and modeling tools.
• The DSS network and architecture.

Hättenschwiler identifies five components in a DSS:

• Users.- With different roles or functions in the decision-making process (decision maker, advisers, domain experts, system experts, data collectors).
• Decision context.- It must be specific and definable.
• Target system.- This describes most of the preferences.
• Knowledge Bases.- Composed of external data sources, knowledge databases, job databases, data warehouses and meta-databases, mathematical models and methods, procedures, inference and search engines, administrative programs , and reporting systems.
• Work environment.- For the preparation, analysis and documentation of alternative decisions.

Arakas proposes a generalized architecture composed of five different parts:

• The data management system.
• The model management system.
• The knowledge engine.
• The user interface.
• The users.

Development Environments

DSS systems are not totally different from other systems and require a structured approach. Sprague and Watson (1993) provided a three-tier environment:

1. Technology levels.- A division into 3 levels of hardware and software for DSS is proposed:
   1. Specific DSS.- Real application that will be used by the user. This is the part of the application that allows decision making on a particular problem. The user will be able to act on this particular problem.
   2. DSS Generator.- This level contains environment hardware and software that allows people to easily develop specific DSS applications. This level makes use of CASE Tool. It also includes special programming languages, function libraries, and linked modules.
   3. DSS tools.- Contains low-level hardware and software.
2. The people who participate.- For the development cycle of a DSS, 5 types of users or participants are suggested:
   1. Final user
   2. Intermediary
   3. Developer
   4. Technical support
   5. Systems expert
3. The development approach.- The approach based on the development of a DSS should be very iterative. This will allow the application to be changed and redesigned at various intervals. The initial problem is used to design the system, and then it is tested and revised to ensure that the desired result is achieved.