https://www.um.edu.mt/library/oar/handle/123456789/4610 2026-07-30T05:32:21Z https://www.um.edu.mt/library/oar/handle/123456789/148267 Title: Do ESG scores and controversies improve corporate financial distress prediction? : evidence from machine learning in Asia-Pacific markets Authors: Raza, Hassan; Zaidi, Syeda Hina; Thalassinos, Eleftherios Abstract: PURPOSE: This study investigates whether ESG information provides incremental predictive value for corporate financial distress beyond established accounting-based predictors. Focusing on twelve Asia-Pacific markets, we evaluate the complete LSEG/Refinitiv ESG framework, including the headline ESG score, pillar and category scores, and the ESG Controversies score, within a rigorous machine-learning framework.; DESIGN/METHODOLOGY/APPROACH: The analysis is based on 47,253 firm-year observations spanning 2016–2024. The benchmark model incorporates the principal predictors established in the financial distress literature, including traditional accounting ratios, liquidity measures, funds-flow indicators, earnings-manipulation variables, and macroeconomic conditions. Model performance is evaluated using a strict out-of-time validation design in which models are trained on 2016–2022 observations and tested exclusively on 2023–2024 data. Gradient boosting and complementary machine-learning algorithms are employed, while SHAP analysis is used to examine feature contributions.; FINDINGS: The results reveal three principal findings. First, ESG coverage is highly selective, encompassing only approximately one-fifth of firm-year observations and declining to negligible levels in frontier markets, while distressed firms are substantially less likely to receive ESG ratings than financially healthy firms. Second, although ESG variables possess modest standalone predictive ability, they provide no incremental improvement once comprehensive financial fundamentals are incorporated into the prediction model. Third, SHAP attribution assigns considerable importance to ESG variables despite their negligible contribution to out-of-time predictive performance, highlighting that feature importance should not be interpreted as evidence of incremental predictive value. Furthermore, the Ushaped relationship between ESG performance and financial distress documented for U.S. firms is not observed across Asia-Pacific markets.; PRACTICAL IMPLICATIONS: This study provides the first comprehensive out-of-time machinelearning assessment of the full LSEG/Refinitiv ESG architecture for corporate financial distress prediction across twelve Asia-Pacific economies.; ORIGINALITY/VALUE: By evaluating ESG information against one of the most comprehensive benchmarks of classical distress predictors, the study demonstrates that ESG ratings currently offer limited incremental value for financial distress prediction in the region, while identifying insufficient ESG coverage as a fundamental constraint for both practitioners and policymakers. 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148266 Title: Public debt, fiscal stability and sustainable competitiveness in the European Union Authors: Ejsmont, Aneta; Wolniak, Radosław; Wilczyńska, Małgorzata; Noworol-Luft, Elżbieta; Ejdys, Stanisław; Solek, Karol; Kolinski, Adam; Barczak, Agnieszka; Walenia, Alina Abstract: PURPOSE: This study examines how public debt influences socio‑economic development and economic competitiveness across the 27 European Union (EU) Member States over the period 2010–2025. Public debt has become a central challenge for fiscal sustainability, shaping countries’ long‑term growth potential, resilience, and the capacity to maintain high living standards.; DESIGN/METHODOLOGY/APPROACH: Using Eurostat data, the analysis evaluates the relationship between public debt, GDP per capita, unemployment, and the Human Development Index (HDI), which serves as a synthetic measure of socio‑economic progress. The study applies comparative analysis and regression modelling to assess how differences in public debt levels correspond with disparities in economic performance and competitiveness.; FINDINGS: The results show a significant increase in public debt across all EU countries between 2010 and 2025, with the highest levels observed in France, Italy, Spain, Germany, and Belgium. The findings indicate that public debt has a negative impact on GDP growth (coefficient –0.3), while economic growth itself contributes to rising debt levels (coefficient 0.4). The strength of these relationships varies considerably across Member States, with the strongest effects observed in Spain and Ireland.; PRACTICAL IMPLICATIONS: The study concludes that excessive public debt poses risks to fiscal stability and long‑term competitiveness, while moderate debt levels may support socio‑economic development.; ORIGINALITY/VALUE: These results highlight the need for sustainable fiscal governance to ensure balanced growth and resilience in the European Union. 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148263 Title: The impact of artificial intelligence on art and creative careers Authors: Arize, Augustine C.; Delanoy, Sophia; Levitchi, Loredana; Malindretos, John; Ndu, Ikechukwu Abstract: PURPOSE: This study investigates the impact of Artificial Intelligence (AI) on art and creative careers, focusing on its economic, cultural, labor-market, and technological implications. The research explores how generative AI is transforming creative production processes, altering employment patterns, and reshaping the value of human creativity in an increasing digital economy.; DESIGN/METHODOLOGY/APPROACH: The study adopts a qualitative and analytical approach based on an extensive review of academic literature, industry reports, and economic forecasts from international organizations, including PwC, Goldman Sachs, OECD, UNESCO, the World Bank, and the World Economic Forum. The analysis examines current trends and future projections related to AI adoption in creative industries, employment transformation, intellectual property challenges, and global economic development.; FINDINGS: The findings indicate that AI is expected to become one of the most influential technologies affecting creative industries during the coming decades. While AI significantly improves productivity, lowers production costs, and expands access to creative tools, it also creates challenges related to job displacement, copyright protection, cultural homogenization, and economic inequality. The study identifies the emergence of new hybrid professions that combine artistic creativity with technological expertise. Furthermore, AIdriven growth is projected to contribute substantially to global economic output while simultaneously transforming traditional creative occupations.; PRACTICAL IMPLICATIONS: The results highlight the importance of workforce reskilling, educational adaptation, and policy development to support creative professionals in an AIdriven environment. Governments, educational institutions, and industry stakeholders must develop strategies that encourage innovation while protecting intellectual property rights, cultural diversity, and employment opportunities.; ORIGINALITY/VALUE: The study contributes to the growing literature on AI and creativity by integrating economic, cultural, labor-market, legal, and environmental perspectives into a comprehensive framework. It provides a forward-looking assessment of how AI may reshape creative careers and the global creator economy while emphasizing the importance of human–AI collaboration. 2026-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/148262 Title: AI-augmented recruitment interviews : a feasibility study of real-time facial video analysis under recruitment-like conditions Authors: Jaworski, Przemysław; Makowski, Miłosz; Pondel, Maciej Abstract: PURPOSE: This paper examines whether real-time facial video analysis can function as an interpretable decision-support layer in technology-mediated recruitment interviews. It addresses a gap between research on AI-supported recruitment, which mainly emphasises efficiency and process standardisation, and research on affect-related video analysis, which typically prioritises model performance outside realistic organisational hiring contexts.; DESIGN/METHODOLOGY/APPROACH: The study adopts a staged research design combining: (1) laboratory grounding through comparison of optically derived facial activity traces with EMG-related measures, (2) development of a remote-capable and interview-compatible capture procedure, and (3) prototype evaluation in recruitment-like scenarios. The analytical pipeline combines convolutional neural network-based landmark detection, FLAME-based facial reconstruction, and FACS-consistent descriptors to transform facial activity recorded from standard video into biosignal-like temporal traces. Recruitment-oriented evaluation was conducted on a sample of 75 participants, with system outputs compared against the ratings of a single expert observer.; FINDINGS: The results indicate prototype-level feasibility rather than validated recruitment effectiveness. The strongest agreement with expert assessment was observed for emotionrelated outputs (85%) and stress-related inference (80%), while lower agreement was found for interactional responsiveness (60%) and nonverbal behaviour based on microexpression analysis (55%). Aggregate agreement reached 75%. The prototype also proved operationally feasible within a structured interview workflow, requiring up to 20 seconds of behavioural observation for selected constructs and generating outputs within near-real-time latency. However, the findings do not establish predictive validity for live hiring decisions.; PRACTICAL IMPLICATIONS: The proposed approach may support structured recruiter observation by providing auditable, standardised, and temporally interpretable behavioural indicators during selected interview segments. Its use should remain strictly supportive, human-supervised, and bounded by governance safeguards relating to privacy, consent, transparency, and fairness.; ORIGINALITY/VALUE: The paper contributes a recruitment-oriented framework that links physiological grounding, remote-capable data collection, and prototype-level expertconcordance testing. Its originality lies in treating facial video analysis not as a tool for autonomous candidate judgement, but as a cautious and reviewable analytical layer designed to support, rather than replace, human decision-making in recruitment. Description: During the preparation of this manuscript, the authors used ChatGPT Business, a generative AI tool developed by OpenAI, solely for language editing purposes, including improvement of grammar, clarity, style, and readability of the text. The tool was not used to generate research data, conduct data analysis, create results, formulate conclusions, or make substantive scientific decisions. All AI-assisted edits were reviewed, verified, and approved by the authors. The authors remain fully responsible for the accuracy, originality, integrity, and final content of the manuscript. 2026-01-01T00:00:00Z