A5006584478- Regional Development and Management Studies
- Financial Distress and Bankruptcy Prediction
- Entrepreneurship Studies and Influences
- Firm Innovation and Growth
- Imbalanced Data Classification Techniques
- Global Trade and Competitiveness
- Credit Risk and Financial Regulations
- Corporate Finance and Governance
- Neural Networks and Applications
- Working Capital and Financial Performance
- Rough Sets and Fuzzy Logic
- Family Business Performance and Succession
- Regional Development and Policy
- Nutritional Studies and Diet
- Forecasting Techniques and Applications
- Obesity, Physical Activity, Diet
- Banking stability, regulation, efficiency
- Financial Reporting and Valuation Research
- Stock Market Forecasting Methods
- Consumer Attitudes and Food Labeling
- Cultural Industries and Urban Development
- Cultural Differences and Values
- Linguistics, Language Diversity, and Identity
- International Business and FDI
- Insurance and Financial Risk Management
University of Osijek
2013-2024
University of Jos
2016
Business students from a public university in Croatia participated an international study on entrepreneurial self-efficacy, identity, and education. The results of this preliminary empirical research indicate that the main predictors intentions are strength identity aspiration self-efficacy. These two constructs mediate number personal, situational, or contextual factors, including Empirical analysis supports majority Social Cognitive Career Theory hypothesized interaction between control...
Abstract Previous research on credit scoring that used statistical and intelligent methods was mostly focused commercial consumer lending. The main purpose of this paper is to extract important features for in small‐business lending a dataset with specific transitional economic conditions using relatively small dataset. To do this, we compare the accuracy best models extracted by different methodologies, such as logistic regression, neural networks (NNs), CART decision trees. Four NN...
The impact of liquidity on the capital structure: a case study Croatian firms Background: Previous studies have shown that in some countries, liquid assets increased leverage while other countries were more frequently financed by their own and therefore less leveraged. Objectives: aim this paper is to investigate structure firms. Methods/Approach: Pearson correlation coefficient applied test relationship between ratios debt ratios, share retained earnings current leverage. Results: A survey...
The paper aims to establish an efficient model for predicting company growth by leveraging the strengths of logistic regression and neural networks.A real dataset Croatian companies was used which described relevant industry sector, financial ratios, income, assets in input space, with a dependent binomial variable indicating whether had high-growth if it annualized more than 20% year over three-year period.Due large number variables, factor analysis performed pre-processing stage order...
The question of what motivates entrepreneurs to maintain and grow their ventures beyond the startup phase remains an underexplored aspect entrepreneurship research. Using data from Global Entrepreneurship Monitor, GEM (2023), this study examines four key entrepreneurial motivations among 103 established Croatian who are making a difference in world, building great wealth or very high income, continuing family tradition, earning living. Employing multivariate multiple regression approach, we...
Determinants of gender-role attitudes were examined in samples university students from Pittsburgh the United States, Ljubljana Slovenia, and Osijek Croatia. Surveys including items Attitudes Toward Women Scale Neosexism administered to a total 1,544 U.S. students, 912 Slovene 996 Croatian between years 1991 2000. As predicted, men held less egalitarian or more sexist about appropriate roles for women men, those with frequent attendance at religious services attitudes. No changes found over...
Since socialism’s decline, abortion has become a divisive political issue in East Central Europe, just as it is the United States. Questionnaires administered to college students Croatia, Czech Republic, Slovenia, and States between 1991 1994 assessed importance of religious identification, degree feelings participation, desired number children, gender role attitudes predictors approval for reasons personal choice. Multiple regression indicated that these variables best predicted level...
The desires to live in another country or emigrate from one's of origin was examined a sample 3200 university students Croatia, the Czech Republic, Poland, Russia, and Slovenia. All these countries have been experiencing economic difficulties during their transition socialist market-driven economies. It hypothesized that who wanted would score higher Achievement Power Motivation also show levels Work Centrality lower Family than those stay origin. Motive predictors were further expected be...
Abstract Background: Large-dimensional data modelling often relies on variable reduction methods in the pre-processing and post-processing stage. However, such a usually provides less information yields lower accuracy of model. Objectives: The aim this paper is to assess high-dimensional classification problem recognizing entrepreneurial intentions students by machine learning methods. Methods/Approach: Four were tested: artificial neural networks, CART trees, support vector machines,...
This study analyses the dynamics, structure and connections between entrepreneurial activity, economic development firm efficiency. While usual presumption on relationship these variables implies straightforward, linear positive impacts, empirical evidence shows that those impacts are significant, more complex less straightforward. The of activity in Croatia early stages entrepreneurship very dynamic volatile. Furthermore, significant inter-regional differences exist performance across six...
Abstract Segmentation in banking for the business client market is traditionally based on size measured terms of income and number employees, statistical clustering methods (e.g. hierarchical clustering, k-means). The goal paper to demonstrate that self-organizing maps (SOM) effectively extend pool possible criteria segmentation with more relevant criteria, including behavioral, demographic, personal, operational, situational, cross-selling products. In order attain paper, dataset clients...
Credit risk is related to the of borrower that lender will not be able return their debt including interest. Numerous researches have been conducted in area credit risk, both using classical models such as Altman Z-score and machine learning methodology. However, research data from Croatian financial institutions scarce, especially focused on selection demographic and/or behavior variables. In addition, it important develop robust estimate accurately possible. The goal this a mining model...
The aim of this paper is to segment retail clients by using adaptive Mahalanobis clustering in a way that each can be suitable for separate credit scoring development such better risk assessment could accomplished.A real data set on from Croatian bank was used the paper.Grouping point carried out partitioning algorithm (see, e.g., [20]).It an incremental algorithm, which recognizes ellipsoidal clusters with main axes directions eigenvectors corresponding covariance matrix set.On basis given...
This study sheds light on the most common issues related to applying logistic regression in prediction models for company growth.The purpose of paper is 1) provide a detailed demonstration steps developing growth model based analysis, 2) discuss pitfalls and methodological errors model, 3) solutions possible ways overcoming these issues.Special attention devoted question satisfying assumptions, selecting defining dependent independent variables, using classification tables ROC curves,...