Aljaž Herman

Mr. Aljaž Herman


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2024 in Information
Verified
Journal Article
Open access
PDF file
TJTimotej of Jagrič
Timotej of Jagrič
AHAljaž Herman
Aljaž Herman
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.

30 October 2025 in Sustainability
Verified
Journal Article
Open access
PDF file
AHAljaž Herman
Aljaž Herman
ZOZan Jan Oplotnik
Zan Jan Oplotnik
TJTimotej of Jagrič
Timotej of Jagrič
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.

24 May 2024 in Information
Verified
Journal Article
Open access
PDF file
TJTimotej of Jagrič
Timotej of Jagrič
DFDušan Fister
Dušan Fister
SGStefan Otto Grbenic
Stefan Otto Grbenic
AHAljaž Herman
Aljaž Herman
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.

27 March 2025 in Information
Verified
Journal Article
Open access
PDF file
TJTimotej of Jagrič
Timotej of Jagrič
DLDavor Luetić
Davor Luetić
DMDAMIJAN MUMEL
DAMIJAN MUMEL
AHAljaž Herman
Aljaž Herman
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.

10 April 2026 in Frontiers in Public Health
Verified
Journal Article
Open access
PDF file
TJTimotej Jagrič
Timotej Jagrič
JZJovan Zubović
Jovan Zubović
AZAleksandar Zdravković
Aleksandar Zdravković
AHAljaž Herman
Aljaž Herman
Background: In low- and middle-income countries like Serbia, improving access to healthcare is a central objective of social and development policy, closely linked to the Sustainable Development Goals, particularly SDG 3 (Good Health and Well-Being) and SDG 8 (Decent Work and Economic Growth). However, healthcare expenditure is still frequently perceived as a fiscal cost rather than as a productive investment. Serbia, an middle-income country with a predominantly publicly financed healthcare system, offers a relevant case for examining how expanding healthcare access is intertwined with domestic economic structures and inclusive development outcomes. Methods: Using national input–output tables for 2019, this study applies standard input–output modelling to estimate output, income, employment, and value-added multipliers associated with the Serbian healthcare sector. The analysis captures direct, indirect, and induced effects, enabling an assessment of how healthcare spending propagates through domestic supply chains and labor markets. Results: The findings show that healthcare in Serbia generates significant economy-wide spillovers that extend well beyond service provision. Output multipliers exceed unity, indicating strong domestic production linkages that support the availability and affordability of healthcare services. Employment multipliers rank healthcare among the leading job-generating sectors, contributing directly to SDG 8 by fostering stable and locally anchored employment. Most notably, the total value-added multiplier places healthcare among the top ten sectors of the Serbian economy, underscoring its capacity to retain expenditure domestically and to reinforce the economic foundations necessary for sustained healthcare access. Conclusion: The results demonstrate that investments aimed at improving healthcare access simultaneously advance broader economic inclusion and sustainable development objectives. Comparative benchmarking with European economies reveals structurally consistent patterns in health-sector integration across income levels, while also highlighting country-specific differences in income and employment transmission. By empirically linking healthcare access to macroeconomic returns, this study provides evidence to support policy frameworks that treat health expenditure as a strategic investment for achieving SDG-aligned, resilient, and inclusive growth in low- and middle-income countries.

12 August 2026 in Sustainability
Verified
Journal Article
Open access
PDF file
TJTimotej of Jagrič
Timotej of Jagrič
SGStefan Otto Grbenic
Stefan Otto Grbenic
AHAljaž Herman
Aljaž Herman
Systematic risk plays a central role in company valuation, enterprise risk management, and sustainable investment. However, conventional approaches primarily rely on historical beta estimates and provide limited insight into the factors associated with future changes in systematic risk. This study develops an AI-supported framework for identifying the determinants of one-year-ahead industry beta coefficients for the US economy by combining macroeconomic variables with risk indicators derived from global news analytics. Annual industry betas published by Damodaran are transformed into monthly observations to align with lagged explanatory variables. The analysis combines macroeconomic indicators with twenty-two artificial intelligence-supported risk categories extracted from the GDELT database, collectively representing Dynamic Sustainability Risk. The empirical results show that historical beta persistence alone does not fully explain future industry beta coefficients. Sustainability-related factors—including ESG, supply-chain, technological, strategic, and labor-market risks—consistently appear among the significant determinants across industries, complementing traditional macroeconomic variables. Furthermore, forward-looking systematic risk is associated with interactions between macroeconomic conditions and dynamic sustainability-related risks rather than with historical financial information alone. Rather than developing a forecasting model, the proposed framework provides an interpretable approach for identifying the macroeconomic and sustainability-related determinants associated with future industry beta coefficients, thereby supporting company valuation, enterprise risk management, and sustainable financial decision-making.