Iskanje po katalogu digitalne knjižnice

Opis: This study explores the characteristics of individual investors in crypto asset markets using machine learning and explainable artificial intelligence (XAI) methods. The primary objective was to identify the most effective model for predicting the likelihood of an individual investing in crypto assets in the future based on demographic, behavioral, and financial factors. Data were collected through an online questionnaire distributed via social media and personal networks, yielding a limited but informative sample. Among the tested models, Efficient Linear SVM and Kernel Naïve Bayes emerged as the most optimal, balancing accuracy and interpretability. XAI techniques, including SHAP and Partial Dependence Plots, revealed that crypto understanding, perceived crypto risks, and perceived crypto benefits were the most influential factors. For individuals with a high likelihood of investing, these factors had a strong positive impact, while they negatively influenced those with a low likelihood. However, for those with a moderate investment likelihood, the effects were mixed, highlighting the transitional nature of this group. The study’s findings provide actionable insights for financial institutions to refine their strategies and improve investor engagement. Furthermore, it underscores the importance of interpretable machine learning in financial behavior analysis and highlights key factors shaping engagement in the evolving crypto market.
Ključne besede: crypto investors, identification, characteristics, machine learning, coarse tree model, artificial intelligence
Objavljeno v DKUM: 09.07.2025; Ogledov: 0; Prenosov: 10
Celotno besedilo (1,58 MB)
Gradivo ima več datotek! Več...

Opis: Machine learning algorithms are increasingly used in a vast spectrum of domains where statistical approaches were previously used. Algorithms such as artificial neural networks, classification, regression trees, or support vector machines provide various advantages over traditional linear regression or discriminant analysis. Advantages such as flexibility, scalability, and improved accuracy in dealing with diverse data types, nonlinear problems, and dimensionality reduction, compared to traditional statistical methods are empirically demonstrated in many previous research papers. In this paper, two machine learning algorithms are compared with one statistical method on highly nonlinear data. Results indicate a high level of effectiveness for machine learning algorithms when dealing with nonlinearity.
Ključne besede: machine learning, decision tree algorithm, artificial neural network, predictive models, data characteristics, nonlinear data, artificial intelligence
Objavljeno v DKUM: 02.07.2025; Ogledov: 0; Prenosov: 7
Celotno besedilo (730,52 KB)
Gradivo ima več datotek! Več...

Opis: Drawing from status characteristics theory, we develop a multilevel model to explain the relationships between gender composition (e.g., female-female supervisor-subordinate dyads, a female majority at the next higher level, and a female majority at the same job level) in the workplace and women's career satisfaction. We hypothesise that working with a female supervisor and a female majority at the same level will be negatively related to women's career satisfaction, while a female majority at the next higher level will be positively related to women's career satisfaction. Moreover, we propose that formal societal (gender-equality) institutions and informal cultural (gender-egalitarian) values, each has a moderating effect on the impact of gender compositions on women's career satisfaction. Our results from a multilevel analysis of 2291 women across 35 societies support the three hypothesised main effects. Whereas institutions that support gender equality weaken the positive effect of working with a female majority at the next higher level, they amplify the negative effect of a female majority at the same hierarchical level. Our findings highlight the complex and paradoxical nature of gender composition effects on women's career satisfaction. We discuss the theoretical contributions of our findings and their implications for the diversity management practices of multinational enterprises.
Ključne besede: career satisfaction, gender status beliefs, intragender competition/ cooperation, queen bee phenomenon, status characteristics theory
Objavljeno v DKUM: 01.07.2025; Ogledov: 0; Prenosov: 2
Celotno besedilo (989,47 KB)
Gradivo ima več datotek! Več...

Opis: The purpose of this study was to explore how children perceive the style and characteristics of illustrations in picture books. It was found that six-year-old children preferred expressionist and surrealist illustrations, whereas four-year-old children preferred expressionist and romantic illustrations. They liked illustrations mostly because they were colorful, but also because they saw familiar motifs and actions in those illustrations. Children are also likely to prefer illustrations that are textile-shaped, illustrations that resemble children’s drawings, and naive, happy illustrations. These findings are consistent with previous studies of children’s preferences for illustrations and serve as a reference point for future studies.
Ključne besede: artistic styles, ilustration characteristics, picture book, preschool child
Objavljeno v DKUM: 18.06.2025; Ogledov: 0; Prenosov: 2
Celotno besedilo (743,71 KB)
Gradivo ima več datotek! Več...

Opis: In the paper, the impact of selected popular perceptions about accounting and the accounting major on the accounting major choice was assessed for the sample of undergraduate business school freshmen. Rather than observing differences between accounting majors' and non-accounting majors' perceptions themselves, a novel approach was used, focused on the observation of differences between accounting majors' and non-accounting majors' personal characteristics, deemed as relevant for their fit with selected popular accounting perceptions. Regression coefficients obtained from regressing these personal characteristics on the accounting major choice variable were used as evidence for the impact of observed accounting perceptions on accounting major choice. Results suggest an important impact of some of the popular accounting perceptions on students' decision whether to major in accounting or not.
Ključne besede: accounting, accounting major choice, accounting perceptions, personal characteristics
Objavljeno v DKUM: 02.06.2025; Ogledov: 0; Prenosov: 7
Celotno besedilo (523,60 KB)
Gradivo ima več datotek! Več...
Gradivo je zbirka in zajema 1 gradivo!