Igor Perko

Evaluating probability of default

Research highlights? Active process management prevents decrease of analytic models accuracy over time. ? Content dependent unification of results is required in a multi-model system. ? Reasoning enabled knowledge management structures provide a content framework. ? Dynamic intelligent agents manage processes upon content rules and environment data. ? Probability of the default evaluation results accuracy is managed over time. For the successful probability of default (PD) evaluation with the application of multiple prediction models two issues should be addressed: the accuracy of the analytic models which decreases over time and the evaluation of results which must be presented in a uniform shape. To deal with these two issues, a multi-agent system (MAS) and knowledge management systems (KMS) based process management system is proposed. The proposed system has two goals: to prevent the PD information quality deterioration by active management of analytical processes and to provide a universal access point allowing the simultaneous use of multiple prediction models.

An Agent Model in BI Knowledge Intensive Environment

The Business Intelligence (BI) traditional goals still stay: provide the right information users in organization with right information at the right time and place. The BI systems by their nature demonstrate as heterogeneous, while all plans to unify them eventually fail. Moreover the expectations of R&D of proactive BI let us conclude, the heterogeneity may become chaotic. We claim that, for mastering such a heterogeneous and dynamic system, a programmatically accessible and self managed knowledge management system, capable of storing and representing the whole content of a BI system is required. The properties of Knowledge Management Structures (KMS), combined with intelligent agents (IA) and Multi-agent systems (MAS) show great capabilities, and have, in limited scope, proved their strengths, acting in heterogeneous svstems. In the following paper we synthesized the state of the art research in the fields of BI, KMS, IA and tried to fill a gap disabling successful application of IA for management of KMS in a dynamical environment. To do so, a model of an IA, capable of reasoning and acting in a dynamic KMS environment and sharing its knowledge is presented.

The efficiency of entrepreneurship policy support for the internationalisation of SMEs: the case of Slovenia

The objective of this paper is to evaluate the efficiency of entrepreneurship policy support for the internationalisation of Small- and Medium-sized Enterprises (SMEs) in Slovenia. For this purpose, the mean importance of the primary motives for entering foreign markets, as well as the barriers to entering and doing business in foreign markets, together with knowledge and expectations about governmental and non-governmental support services, were measured in the first part of this research. In the second part, the web portal of the central Slovenian institution for entrepreneurship acceleration – Public Agency for Entrepreneurship and Foreign Investment (PAEFI) – was analysed. The last part of our research comprised website analyses of institutional support for the internationalisation of SMEs, in three other selected member states of the European Union. The study highlights the low awareness and negative experiences of Slovenian SMEs with institutional support for the internationalisation of SMEs.

Big Data for Business Ecosystem Players

Abstract In the provided research, some of the Big Data most prospective usage domains connect with distinguished player groups found in the business ecosystem. Literature analysis is used to identify the state of the art of Big Data related research in the major domains of its use-namely, individual marketing, health treatment, work opportunities, financial services, and security enforcement. System theory was used to identify business ecosystem major player types disrupted by Big Data: individuals, small and mid-sized enterprises, large organizations, information providers, and regulators. Relationships between the domains and players were explained through new Big Data opportunities and threats and by players’ responsive strategies. System dynamics was used to visualize relationships in the provided model.

Sharing business partner behavior

Purpose – The new concept of business partner behavior sharing practice is addressed from three perspectives: technical/technological, legal and ethical/moral with the aim to elaborate its sharing feasibility, value added, legal restrictions and moral considerations. Research results are synthetized to present an overview on business partners behavior sharing direct and indirect value added, costs and risks and proposing mitigation strategies. The paper aims to discuss these issues. Design/methodology/approach – To evaluate technical feasibility, a real-life sharing experiment is conducted. Using a sharing agency data are collected, summarized and reported. For the purpose of legal evaluation, relevant legislation is analyzed. Ethicality/morality is assessed utilizing theoretical applied-ethics analysis. Two major normative moral theories – teleology and deontology – are selected for this purpose. The synthesis of the research results is represented in system dynamics model. Findings – Results show no sig...

Behaviour-based short-term invoice probability of default evaluation

In this paper, the effect of behavioural analytics on short-term default predictions at the invoice level is addressed by answering a question that slightly diverges from the traditional probability of default definition: ‘What is the probability that this invoice will be paid within the next 30 days?’ Resultantly improving short-term liquidity planning accuracy and supporting financial management in companies.