Name
Katsko Igor Aleksandrovich
Scholastic degree
•
Academic rank
associated professor
Honorary rank
—
Organization, job position
Kuban State Agrarian University
Web site url
—
Articles count: 8
The research is devoted to the problem of choosing the best methods for assessing the economic efficiency of information technologies. Using the Kemeny median is proposed to solve this problem. This method will allow to obtain the ranking of methods of evaluating of IT effectiveness by various criteria. The existing methods of valuation of economic efficiency of information technology were systematized in the article. Preliminarily, all the methods were divided into three groups: financial, probabilistic and qualitative analysis tools. The advantages and disadvantages of methods, their purpose, use and limitations were also considered. As a result of systematization, it was concluded that there were some limited and one-sided methods. No single method allows to assess comprehensively the effectiveness of an information technology. Obviously, the methods should be considered in the system. But for this they need to be ranked. In order to obtain the ranking the method of Kemeny median was used. In the beginning the expert evaluation of methods by the eight proposed criteria (taking into account the specificity of the original data, validity, unambiguity, information content, exactness, complexity, the access to information, the cost) was carried out. Next, the search of the group ranking was carried. The matrix of losses was compiled. The problem of appointments was solved in MS Excel. At the end, the matrix of paired comparisons has been obtained. This matrix helped to determine the final ranking of alternative methods. Therefore, using the Kemeny median allowed us to prioritize the use of methods of evaluating of the effectiveness of information technology
The research is devoted to the problem of selecting the
software acquisition method for the company. To solve
this problem the decision support system which allows
automating the process of selecting the software
acquisition method was developed. The existing
methods of software acquisition were reviewed in the
article, as well as the analysis of possibility of their
comparison was conducted. This analysis showed that
the research should be limited to two alternatives -
purchase of licensed program and using Software as a
Service (SaaS). We substantiated the necessity of a
mechanism that would allow the company to
determine with a high degree of accuracy which
software acquisition method was the most preferred.
This mechanism was implemented in the framework of
a decision support system consisting of three main
blocks: database, model base and interface.
The basis of the model base consisted of indicators
calculated on the various methods for assessing the
economic efficiency of information technologies. The
above methods were ranked in descending order of
their informativeness. Based on these results the
algorithm of choice of software, the acquisition
method was proposed. This algorithm formed the basis
of the decision support system which block diagram is
also presented in the article. It is expected that the
developed decision support system will enhance the
validity of the decisions made, reduce the complexity
of the calculations, and minimize losses associated
with acceptance of erroneous decisions
Comparative analysis of intellectual data analysis
methods application and regressive data analysis on
the example of modeling of grains yielding dependence
on expenditures, by data on activities of agricultural
organizations of Krasnodar region for 2006 is carried out in the article. Two approaches: regression with rupture, based on the classical variant and realized in the packet
“Statistica”; multi parametric linear regression, based on the ideology of evolutional programming are carried out in the article. There was made a conclusion on the basis of the analysis results that it was impossible to be
restricted only by one point of view – and regression
in Statistica and analogous means in system PolyAnalyst mutually supplement each other in the description of
investigating process.
There are many ways to improve the decisionmaking
process, but, with a big amount of data and
complexity of decision-making trees, it's becoming
more and more complicated to keep up with the flow
of information coming from many spheres of modern
life. Therefore, the development of various problemsolving
approaches has become an important step in
changing the face of existing technological systems.
This idea appeared in the work of an American scientist
J. Perl who, in 1988, founded a new probabilistic
approach to artificial intelligence and developed
principles of Bayesian Network. Bayesian Network is
a graphical model that represents a set of random
variables and their conditional dependencies. In the
article, the most valuable parts of the given topic
have been reviewed, cognitive maps have been compared
with their partial manifestation - Bayesian
Network; also, one of the options to practically use
such models in the audit field has been analyzed by
observing a possible decision-making process of giving
a modified or unmodified opinion
This article surveys the available statistical services in modern search engines. The statistical results are dis-cussed on the example of Russia's accession to the WTO
The analysis of the modern condition and prospects of development of informational supply of agricultural enterprises is carried out