1. Identifying key risks for nonfinancial companiesTimotej Jagrič, Stefan Otto Grbenic, Aljaž Herman, Maša Galun, 2025, original scientific article Abstract: This month’s edition of the IFAI Global Risk Radar offers a comprehensive assessment of global risk signals, derived from news sources worldwide and IFAI’s expanded taxonomy of financial, operational, environmental, market, geopolitical, and systemic risks. The analysis indicates a marked divergence among risk groups, with customer-facing risks, organisational culture, and operational disruptions exhibiting elevated Risk Frequency Indicators, while environment-related and ESG-linked risks remain in a cooling phase. At the individual-risk level, corruption and fraud, change-management failures, and water-supply crises show the strongest upward deviations relative to historical patterns, reffecting a broader global environment characterised by governance concerns, infrastructure fragilities, and climate-related stress. Several high-frequency indicators display co-movements that align with recent geopolitical escalation, heightened market volatility, and tightening financial conditions in multiple regions. These findings align with recent international policy reports that document persistent inffationary pressures (IMF, 2025), governance-related vulnerabilities (OECD, 2025a), and rising political instability in several emerging markets (World Bank, 2025). For companies, the implications are substantial: a combination of structural shocks, rapid shifts in investor sentiment, and intensifying supply-chain fragility requires a more adaptive and data-driven risk management approach.
Keywords: risk register, AI detection risk model, high frequencies analysis
Published in DKUM: 12.12.2025; Views: 0; Downloads: 3
 Full text (1,06 MB) |
2. The impact of ESG on business performance : anǂempirical analysis of NASDAQ–NYSE-Listed companiesAljaž Herman, Žan Oplotnik, Timotej Jagrič, 2025, original scientific article Abstract: This study investigates the relationship between ESG ratings and a firm’s financial performance, focusing on Return on Assets (ROA) and Return on Equity (ROE). Using a combination of stepwise linear regression and feedforward neural networks (FFNN), we assess both the linear and nonlinear effects of ESG on financial performance. The regression models identify ESG as a significant, positively correlated factor in explaining financial performance, alongside firm demographics, sector affiliation, and financial indicators. Neural networks reveal nonlinear dynamics, particularly for ROA, suggesting threshold effects in the ESG–performance relationship. Sensitivity analysis confirms that ESG’s influence strengthens at higher values. Our findings highlight that ESG is not only statistically relevant but also interacts with firm characteristics in complex ways. These results contribute to the ongoing discourse on sustainable finance by showing that ESG can be a meaningful driver of financial outcomes, especially when modeled through nonlinear approaches.
Keywords: ESG, financial performance, ROA, ROE, regression, neural network
Published in DKUM: 06.11.2025; Views: 0; Downloads: 9
Full text (411,40 KB)
This document has many files! More... |
3. Detecting potential investors in crypto assets : insights from machine learning models and explainable AITimotej Jagrič, Aljaž Herman, Davor Luetić, Damijan Mumel, 2025, original scientific article Abstract: 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.
Keywords: crypto investors, identification, characteristics, machine learning, coarse tree model, artificial intelligence
Published in DKUM: 09.07.2025; Views: 0; Downloads: 13
Full text (1,58 MB)
This document has many files! More... |
4. Meta analysis of business valuation solutions –are AI based methods better?Aljaž Herman, Damijan Mumel, Timotej Jagrič, 2024, review article Abstract: Purpose of the article–this article addresses the challenge of accurately assessing business value in today's dynamic environment, exploring the limitations of traditional valuation methods and the potential of modern, technology-driven approaches.Research methodology–the study uses qualitative research methods, including content analysis, deductive reasoning, and comparative analysis, to review various business valuation techniques.Findings –the research finds that traditional methods like Discounted Cash Flow and Relative Valuation are outdated, failing to capture all value factors. Modern approaches, such as simulation-based valuation, machine learning, and neural networks, combine traditional methods with advanced techniques. These methodologies utilize vast datasets and sophisticated algorithms, enhancing predictive accuracy and understanding of market dynamics. Neural networks excel in analysing complex patterns and adapting to market shifts. However, no single method can capture all nuances, necessitating diverse approaches and acknowledging the subjective nature of valuations
Keywords: business valuation, traditional and advanced valuation methods, machine learning, neural networks, artificial intelligence
Published in DKUM: 01.07.2025; Views: 0; Downloads: 13
Full text (577,12 KB)
This document has many files! More... |
5. AI model for industry classification based on website dataTimotej Jagrič, Aljaž Herman, 2024, original scientific article Abstract: This paper presents a broad study on the application of the BERT (Bidirectional Encoder Representations from Transformers) model for multiclass text classification, specifically focusing on categorizing business descriptions into 1 of 13 distinct industry categories. The study involved a detailed fine-tuning phase resulting in a consistent decrease in training loss, indicative of the model’s learning efficacy. Subsequent validation on a separate dataset revealed the model’s robust performance, with classification accuracies ranging from 83.5% to 92.6% across different industry classes. Our model showed a high overall accuracy of 88.23%, coupled with a robust F1 score of 0.88. These results highlight the model’s ability to capture and utilize the nuanced features of text data pertinent to various industries. The model has the capability to harness real-time web data, thereby enabling the utilization of the latest and most up-to-date information affecting to the company’s product portfolio. Based on the model’s performance and its characteristics, we believe that the process of relative valuation can be drastically improved.
Keywords: industry classification, BERT transformer, business descriptions, multiclass text classification, AI
Published in DKUM: 01.07.2025; Views: 0; Downloads: 12
Full text (1,01 MB)
This document has many files! More... |
6. Private firm valuation using multiples : can artificial intelligence algorithms learn better peer groups?Timotej Jagrič, Dušan Fister, Stefan Otto Grbenic, Aljaž Herman, 2024, original scientific article Abstract: Forming optimal peer groups is a crucial step in multiplier valuation. Among others, the traditional regression methodology requires the definition of the optimal set of peer selection criteria and the optimal size of the peer group a priori. Since there exists no universally applicable set of closed and complementary rules on selection criteria due to the complexity and the diverse nature of firms, this research exclusively examines unlisted companies, rendering direct comparisons with existing studies impractical. To address this, we developed a bespoke benchmark model through rigorous regression analysis. Our aim was to juxtapose its outcomes with our unique approach, enriching the understanding of unlisted company transaction dynamics. To stretch the performance of the linear regression method to the maximum, various datasets on selection criteria (full as well as F- and NCA-optimized) were employed. Using a sample of over 20,000 private firm transactions, model performance was evaluated employing multiplier prediction error measures (emphasizing bias and accuracy) as well as prediction superiority directly. Emphasizing five enterprise and equity value multiples, the results allow for the overall conclusion that the self-organizing map algorithm outperforms the traditional linear regression model in both minimizing the valuation error as measured by the multiplier prediction error measures as well as in direct prediction superiority. Consequently, the machine learning methodology offers a promising way to improve peer selection in private firm multiplier valuation.
Keywords: private firm valuation, multiples, peer group, peer selection, artificial intelligence, self-organizing map
Published in DKUM: 01.07.2025; Views: 0; Downloads: 5
Full text (673,36 KB)
This document has many files! More... |
7. Modeliranje cen nepremičnin - primer stanovanjskih hiš : na študijskem programu 2. stopnje MatematikaAljaž Herman, 2023, master's thesis Abstract: V nalogi bo obravnavan model napovedi oz. ocene cene nepremičnin za primer stanovanjskih hiš, ki temelji na principu multiple regresije. Analiza, ocena parametrov in testiranje ustreznosti modela bo izvedeno na osnovi realnih podatkov, pridobljenih iz Evidence trga nepremičnin. Vzorec zajema podatke za obdobje od 2007 do 2022.
V prvem delu naloge so predstavljena teoretična izhodišča funkcij in metod, ki so uporabljene pri izgradnji modela. Sledi poglavje o postopkih vrednotenja, kjer so opisane spremenljivke, funkcijske oblike modelov in mere primernosti ter ustreznosti. Zadnji sklop
zajema opis postopka izgradnje modela in samo analizo rezultatov.
Keywords: nepremičninski trg, stanovanjske hiše, modeliranje, regresija, cenilka najmanjših kvadratov
Published in DKUM: 07.09.2023; Views: 394; Downloads: 111
Full text (480,04 KB) |
