+7 (495) 987 43 74
Join us -              
Рус   |   Eng

Authors

Shpolyanskaya Irina Yu.

Degree
Dr. Sci. (Econ.), Associate Professor, Professor, Department of Information Systems and Applied Informatics, Rostov State University of Economics (RSUE)
E-mail
irinaspol@yandex.ru
Location
Rostov-on-Don
Articles

Architecture of adaptive Web-based system of Customer Relationship Management based on Web Mining technology

The purpose of this paper is to present the architecture of the CRM system that uses Web Mining techniques and the principles of adaptive management. Adaptive model of customer relationship management in the Web CRM system based on Web Mining technologies is represented in the following form. The core of the CRM system is an adaptive website, based on dynamic analysis of the web resources information usage in order to modify the web site ontology and its personalization to improve user interaction. The system uses online methods to capture useful information from user log file data and browsing pages to analyze customers’ behavior, their preferences regarding different groups of goods and services of the company. The obtained data are structured using the cluster analysis, classification, and association rule mining in order to determine groups of customers and prospects with similar characteristics and behavior. Based on this analysis valuable consumer segments are determined according to the current customer value. For each group of customers system forms the most effective strategy for interaction. To develop adaptive strategies for interacting with customers the proposed model uses the self-organizing learning algorithms. As a result, when using an adaptive approach in Web CRM system forms a closed loop feedback, which allows in real time to adjust the strategy of interaction with customer according to his current preferences and constraints.
Read more...

Fuzzy model for assessing the quality of the portal of the university for effective promotion of educational services

Web technologies and e-marketing provide universities with new opportunities to organize more effective interaction with consumers of educational services. The website of the University becomes an effective marketing tool for attracting consumers of educational services and forming a positive image of the University in the conditions of growing competition. In the process of development and implementation of educational websites, there is a problem of determining the most effective methods of organization and online promotion of websites in order to use them as a marketing tool to attract the greatest number of potential applicants to the University. The main problem that limits the possibility of using the educational website as an effective e-marketing tool is the lack of procedures for evaluating the quality of the portal. The quality of the website is a determining condition for attracting new users and assuring the satisfaction and loyalty of potential and existing consumers of educational services. Therefore, the development of a quality assessment system for an educational website becomes an important requirement in the organization of user feedback for continuous improvement of marketing communications of the educational institution. The article introduces a model for assessing the quality of the University website for effective promotion of educational services, and a method that use expert estimation and fuzzy logic.
Read more...

Quality analysis of information system microservices based on fuzzy model

The paper deals with the analysis of the microservices architecture quality, which is one of the fundamental software trends to the development and maintenance of modern information systems. The selection of the optimal set of microservices implementing information system business processes with a given level of service quality is an important task to improve the efficiency of the system. The solution of this problem occurs under conditions of high uncertainty due to the lack of data, the complexity of the description of the functional relationships, that determine the quality of microservices assigned to business tasks of information system. Integral assessment of the quality of microservices depends on functional (qualitative) and non-functional (quantitative) parameters, which adds complexity to the solution of this problem. Existing approaches to the problem do not fully take into account all the factors that determine such a choice. Implementation of continuous delivery of software components for dynamic business processes can be carried out by different sets of microservices, the optimal choice, and composition of which is a complex multi-alternative task. A fuzzy model is proposed for the selection of a set of microservices with specified levels of service quality. An example shows the possibility of the microservices-based architecture quality assessment using a fuzzy approach.
Read more...

Semantic technologies in the online learning support system

This paper presents a new approach to solving the problem of personalization of learning in a dynamic electronic environment. To make recommendations to students on choosing the most suitable online course, a semantically approach is used, based on the representation and use of knowledge about the subject area of e-learning and the characteristics of the student. Within the framework of this approach, a method of using OWL-ontology for integrating resources into an individual learning trajectory is proposed. Ontologies provide a more adequate representation of online resources and compatibility of the user request format with descriptions of education resources from different developers. The architecture of the e-learning support system for the selection of online resources for their further inclusion in the individual trajectory of student learning is defined. The recommendation system analyzes the context of the user profile to generate recommendations for the content of the training course. The system uses information from user profiles and queries to find a semantic match between the course information and the user profi of the student. The developed system is implemented as a set of personal agents and services that interact based on a knowledgebase represented as a set of interconnected ontological models. The system recommends a resource based on current requests and user characteristics regarding their profile. In the process, the system dynamically updates the knowledge base about the current user characteristics, thereby increasing the effectiveness of generated recommendations. Based on the recommendations received, the user can choose the most appropriate version of the composition of educational materials, taking into account their level of knowledge and their preferences. Read more...

Models and methods of reinforcement learning in the structure of adaptive web-based information systems

Widespread use of web-based systems in business, marketing, e-learning, etc. makes it necessary to take into account and analyze the information needs of the user in order to optimize interaction with him. One of the main problems of creating adaptive web-based systems is the task of classifying information resources (pages) of the portal describing the offered product or service, for the subsequent formation of the user profile and personalized recommendations of services. Data mining and machine learning methods can be used to solve this problem. The article presents a new approach to creating adaptive web-based information systems using the reinforcement learning algorithms to classify information resources and to form personalized recommendations to users based on their preferences. An adaptive approach is proposed and justified, based on the use of Reinforcement Learning procedures, which allows you to automatically find the most effective strategies for the correct classification of the site's resources and the formation of user groups with the same type of requests and preferences. The proposed scheme allows you to create procedures for evaluating and ranking information resources of the system based on the analysis of user behavior on the site online. The reinforcement learning algorithms used make it possible to evaluate the relevance of each page of the site to the requests and preferences of the users from different categories in order to optimize the structure and content of the site, as well as to build an effective system of recommendations in accordance with the user's interests to be able to choose the most suitable products or services. Read more...