Jerzy Korczak

Multi-criteria evaluation of the intelligent dashboard for SME managers based on scorecard framework

The article presents an approach to evaluate the Decision Support System applied in the InKoM project. The evaluation method is based on a scorecard framework, oriented towards Business Intelligence (BI) systems and projects dedicated to the management supporting of small and medium enterprises (SME). To design the method, known existing commercial and no commercial BI maturity models, usability standards, and scorecard frameworks have been analyzed and adapted to SMEs area. Notably, the scorecard framework was extended to the new evaluation criteria associated with innovative knowledge-based functions created in the InKoM project, especially such as ontologies of economic and financial knowledge, and visual navigation and exploratory interface based on topic maps. The main elements of the scorecard framework and usage in InKoM of multi-criteria evaluation are illustrated and discussed in this paper.

Process of Ontology Design for Business Intelligence System

Business Intelligence systems tend more and more towards semantically rich functionalities. One of the main artefacts to create a semantic network is the ontology. There are many methods describing the procedure of creating ontology for information solutions. The article presents the approach to the conceptualisation of the financial knowledge for a Business Intelligence system. The content of the knowledge is focused on essential financial concepts and relationships related to the management of small and medium enterprises (SME). That includes the illustration of the process of conceptualization of the financial ontology, which can be implemented in the Business Intelligence system.

Design of "Business Informatics" Study Program Model, Curriculum and Perspectives

In this paper a study program of “Business Informatics” at the Wroclaw University of Economics, Poland, is presented. The structure of subjects taught and organization of the curriculum for Bachelor and Master levels are detailed. The education model is presented along with descriptions of profession-oriented modules. The authors discussed also a comparison of the new program of Business Informatics and a previous one, called “Informatics and Econometrics” that was common and official program of applied informatics in business schools in Poland. The perspectives and the constraints of program implementation of the new field of study are indicated.

Fuzzy Logic as Agents’ Knowledge Representation in A-Trader System

The paper presents the application of a fuzzy logic in building the trading agents of the A-Trader system. A-Trader is a multi-agent system that supports investment decisions on the FOREX market. The first part of the article contains a discussion related to the use of fuzzy logic as representation of an agent’s knowledge. Next, the algorithms of the selected fuzzy logic buy-sell decision agents are presented. In the last part of the article the agent performance is evaluated on real FOREX data.

Conceptual design of financial ontology

The article presents the approach to the conceptualization of the financial knowledge used for an Intelligent Dashboard for Managers. The content of the knowledge is focused on essential financial concepts and relationships related to the management of small and medium enterprises (SME). That includes the illustration of the conceptualization of the ontology. The designed ontology was split into six ontologies describing areas of Cash Flow at Risk, Comprehensive Risk Measurement, Early Warning Models, Credit Scoring, Financial Market, and General Financial Knowledge. The examples of the topic map of key financial indicators and their interpretation are given. The results of this research have been implemented in the Business Intelligence system.

Towards process-oriented ontology for financial analysis

The article presents an approach to integrate a business process knowledge of Decision Support Systems. It concerns two major aspects of the system, i.e. the formalization of processes predefined in Business Process Modeling Notation, the reuse of a domain ontology, and the analysis of economic and financial information. The described approach is a continuation of the construction of the intelligent cockpit for managers (InKoM project), whose main objective was to facilitate financial analysis and the evaluation of the economic status of the company in a competitive market. The current project is related to the design of smart decision support systems based on static (structural) and procedural knowledge. The content of the knowledge is focused on essential financial concepts and relationships related to the management of small and medium enterprises (SME). An experiment was carried out on real financial data extracted from the financial information system.

Fundamental analysis in the multi-agent trading system

The paper presents issues related to developing methods for fundamental analysis used to expand capabilities of multi-agent trading system, to better predict the financial market. The fundamental analysis indicators can be used as confirmation of decisions generated by other strategies of the system. The first part of the article discusses briefly the fundamental analysis issues in relation to the online trading on FOREX market. The statistical analysis of correlations of the different time series indicators and algorithms of fundamental analysis agents are examined. The final part discusses the results of the performance evaluation of selected investment strategies, including fundamental-based agents.

Attempt to extend knowledge of Decision Support Systems for small and medium-sized enterprises

The article presents a proposal to extend the functionality and knowledge of Business Intelligence systems to answer the requirements of managers of small and medium-sized enterprises (SMEs). It concerns two major aspects of the system, i.e. the interface that takes into account the level of knowledge of the manager, and supports the interpretation of economic and financial information using the built-in domain ontologies. The project is related to the design of smart decision support systems based on financial ontology and on the model of manager knowledge created by eye tracking analysis. An experiment was carried out on real financial data extracted from the database of Business Intelligent BINOCLE, developed by Bilander Co. To create a model of manager knowledge, a number of financial analysts, experts and economists were invited to analyze the pre-defined financial reports. Their tasks were observed and analyzed by the eye-tracking system StudioTM, Tobii. The logs of the system as well as the financial ontology have been used to develop the intelligent interface of a Decision Support System.

An approach to discover false alarms in monitoring system of the copper mine

The key task of telecommunication systems in deep mining is to ensure safety and continuity of production. These systems, despite modern and innovative infrastructure monitoring solutions, are not free from drawbacks. The occurrence of false alarms of damage to infrastructure is the practical problem which causes many negative effects, such as increasing the cost of the current operation of the system, information overload of operators, and service errors. In this paper a method for detecting false alarms in the communication system of the copper mine is proposed, presenting some rules that provide useful knowledge extracted from the database. A variety of experiments were carried out on real data from the telecommunications system operating in the copper mine KGHM Polska Miedź S.A.

Visual Exploration of Functional MRI Data

Exploration of sequences of brain images that represent real activity is, in general, a very difficult task not only because of the brain complexity, but also because of a weak signal-to-noise ratio and of the presence of artefacts. The first applications of the classical data mining algorithms showed that their performances and their qualities of recognition are weak. In this article, a new interactive data-driven approach to fMRI image mining is presented, allowing the online observation of cerebral zones. Several non-supervised classification algorithms have been developed and tested on sequences of fMRI images. The results of the tests have shown a strong influence on the classifier performances by the number of classes, signal-tonoise ratio, and volumes of activated and explored zones.