EXPERT SYSTEMS AND SUPPORT SYSTEMS FOR DECISION-MAKING
Business decision support systems
In the 1980s. American and Japanese companies began to develop information systems that differed dramatically from the management information systems for the support of production activities (Managerial Information System - MIS). These systems were initiated by the process of "intellectualization" IP. The new systems were more compact and interactive, and their goal was to help end-users work with all types of data, conduct analytical studies, build models, and play scenarios to solve weakly structured and generally unstructured problems in innovative projects. Systems providing such capabilities are called decision support systems - DSS ( Decision Support System - DSS ) [Turban E., abc.org.ru/smd.html].
In the mid-1980s, such systems became widely used in the current activities of large companies and corporations. Currently, DSS is an obligatory part of CIS (Figure 12.1).
The following are the key features and functionality of decision support systems:
• providing information support for making decisions on problems that can not be determined in advance;
• Application of complex multidimensional and multivariate analysis and modeling tools;
Fig. 12.1. The general structure of the decision support information subsystem
• Flexibility of use, adaptability to specific situations;
• the ability to dynamically manipulate input data;
• the most user-friendly user interface, which allows you to work with virtually no programmers.
Specialized DSS subsystems are used, as a rule, at the top and middle management levels by the enterprise. Heads of the company and leading managers can use the financial modules of the DSS to predict the growth or decline in the efficiency of using the company's assets when the business activity or economic situation in the country changes. Mid-level managers the same system can be useful for assessing the prospects for short-term investments in projects under implementation. For project managers, this is a tool for financial and resource planning and distribution of funds for planned purchases.
DSSs usually consist of the following standard components: software core, data storage, analytical data processing and analysis tools, visualization and presentation facilities, telecommunications devices.
The data warehouse provides a single environment for storing corporate data organized into structures and optimized for performing analytical operations.
Analytical tools allow the end user, who does not have special knowledge in the field of information technology, to navigate and present data in terms of the subject area. For users of different qualifications, DSSs have different types of interfaces for accessing their services (Figure 12.2).
Analytical systems allow solving three main tasks: analysis of heterogeneous multidimensional information of different degree of formalization in real time, subsequent intellectual analysis of data with building business case models and keeping records.
Fig. 12.2. Basic components of the DSS
DSS systems are part of the "intelligent enterprise resources" or intelligent business analysis tools (Business Intelligence - BI). An important part of B1-technologies are also systems of intellectual information search (Data Mining - DM). Data Mining is the process of discovering in raw data previously unknown, non-trivial, practically useful and accessible for interpretation of knowledge necessary for making decisions in various fields. Data Mining technologies are of great value for managers and analysts in their day-to-day operations. Business people realized that with the help of Data Mining methods they can get tangible advantages in the competition.
The basis of modern technology Data Mining (Discovery-driven Data Mining) is based on the concept of patterns (Patterns), reflecting fragments of multidimensional relationships, available in the "raw" data. These patterns represent the patterns inherent in the data samples that can be compactly expressed in a human-readable form. The search for templates is done using methods that are not limited to the a priori assumptions about the structure of the sample and the type of distributions of the values of the analyzed indicators. In Fig. Figure 12.3 shows the data conversion scheme using Data Mining technology.
Fig. 12.3. Data Mining Conversion Scheme
The basis for all kinds of forecasting systems is historical information (i.e., data samples placed in chronological order) stored in databases and data stores in the form of time series. If it is possible to build templates that adequately reflect the dynamics of the behavior of the target indicators, it is likely that with their help it is possible to predict the behavior of the system in the future. In Fig. Figure 12.4 shows the full cycle of Data Mining.
Fig. 12.4. Cyclic Data Mining Application
The important position of Data Mining is the non-triviality of the patterns sought by templates. This means that they must reflect non-obvious, unexpected (Unexpected) regularities in the data that constitute the so-called hidden knowledge (Hidden Knowledge). Business people have come to understand that the "raw" The data (Raw Data) contains a deep layer of knowledge and, with proper digging, "real nuggets" can be found that can be used in competition.
Data Mining is a multidisciplinary field that has arisen and is developing on the basis of achievements in applied statistics, pattern recognition, artificial intelligence methods, database theory, etc. (Figure 12.5). Hence the abundance of methods and algorithms implemented in various operating systems Data Mining. [Duke VA inftech.webservis.ru/it/datamining/ar2.html].
Fig. 12.5. Some areas of application of Data Mining technology
You can name five standard types of regularities, detected using Data Mining methods: association, sequence, classification, clustering and forecasting.
Association takes place when several events are related to each other. For example, a survey conducted in a computer supermarket may show that 55% of computer buyers also purchase a printer or scanner; and in the presence of discounts for such a set the printer is purchased in 80% of cases. With information about such a correlation, managers can easily assess how useful the discount is.
If there is a chain of time-related events, then they say about sequences. So, for example, after buying a house in 45% of cases within a month, a new stove is purchased, and Within two weeks 60% of new settlers get refrigerators and air conditioners.
Using classifications , you identify the characteristics that characterize the group to which the object belongs. This is done by analyzing already classified objects and formulating a set of rules.
Clustering differs from the classification in that data groups are pre-defined. With the help of clustering, Data Mining tools independently separate different homogeneous data groups.
Found on the given characteristics and structured by certain rules, the data is processed using specialized software tools - statistical data processing packages.
The latest versions of almost all known statistical packages include, along with traditional statistical methods, also Data Mining elements. But the main attention in them is given still to classical methods - correlation, regression, multifactor analysis, etc. As examples of the most powerful and widespread statistical packages one can name SAS (SAS Institute), SPSS (SPSS), STATGRAPHICS (Manugistics company), STATISTICA for WINDOWS, STADIA, etc. These packages can be successfully used by small and medium-sized enterprises, and large multidisciplinary companies can integrate them into the overall corporate network.
Also We Can Offer!
- Argumentative essay
- Best college essays
- Buy custom essays online
- Buy essay online
- Cheap essay
- Cheap essay writing service
- Cheap writing service
- College essay
- College essay introduction
- College essay writing service
- Compare and contrast essay
- Custom essay
- Custom essay writing service
- Custom essays writing services
- Death penalty essay
- Do my essay
- Essay about love
- Essay about yourself
- Essay help
- Essay writing help
- Essay writing service reviews
- Essays online
- Fast food essay
- George orwell essays
- Human rights essay
- Narrative essay
- Pay to write essay
- Personal essay for college
- Personal narrative essay
- Persuasive writing
- Write my essay
- Write my essay for me cheap
- Writing a scholarship essay