FinTech, Volume 4, Issue 4 (December 2025) – 9 articles

Economic disinformation causes significant harm, resulting in substantial losses for the global economy. Each year, it is estimated that around USD 78 billion is lost due to the spread of false or misleading information, with a major share stemming from stock market fluctuations and misguided decisions. In Croatia, the rapid spread of economic misinformation further threatens decision-making and institutional credibility. The EkonInfoChecker project was established to address this issue by combining human fact-checking with AI-based detection. This paper presents the project’s AI component, which adapts English-language datasets (FakeNews Corpus 1.0 and WELFake) into Croatian, yielding over 170,000 articles in economics, finance, and business. We trained and evaluated six models—FastText, NBSVM, BiGRU, BERT, DistilBERT, and the Croatian-specific BERTić—using precision, recall, F1-score, and ROC-AUC. Results show that transformer-based models consistently outperform traditional approaches, with BERTić achieving the highest accuracy, reflecting its advantage as a language-specific model. The study demonstrates that AI can effectively support fact-checking by pre-screening economic content and flagging high-risk items for human review. However, limitations include reliance on translated datasets, reduced performance on complex categories such as satire and pseudoscience, and challenges in generalizing to real-time Croatian media. These findings underscore the need for native datasets, hybrid human-AI workflows, and governance aligned with the EU AI Act. Full article

In this study, we review recent research on how digital payment technologies (DPTs) promote financial inclusion (FI) across the world. Drawing on empirical studies from the past decade, we show that digital payment systems have helped reduce financial exclusion—particularly in developing economies—by expanding access to essential financial services for underserved groups. The paper also highlights the role of demographic factors such as age and gender, with evidence of higher adoption among youth and women. We identify the main indicators used to measure digital payment adoption and FI, providing a foundation for future empirical analysis. To deepen understanding, we call for combining macroeconomic data with rigorous econometric approaches to better capture how DPTs contribute to inclusive financial systems. The paper further discusses how emerging innovations—including blockchain, artificial intelligence, cloud computing, and biometric authentication—are improving the efficiency, security, and accessibility of digital payments. Together, these technologies are likely to accelerate the transition toward fully digital financial ecosystems and expand the potential for inclusive and sustainable growth. Full article

In this study, we empirically examine the determinants of fundraising success in Japan’s lending-based crowdfunding (LBCF), with a focus on the financial literacy of investors. Using 465 campaigns on the LBCF platform “Bankers” (December 2020–September 2024), we test two predictions derived from the lack of financial literacy hypothesis: (H1) investors are influenced by peripheral signals; (H2) diagnostic signals are not properly evaluated. Both are rejected. In cross-sectional tests, peripheral cues such as “Perks” are negatively associated with success, and the effects of “Title length” and “Purple highlighted text” observed in simpler models vanish when analyzed jointly. By contrast, diagnostic information is consistently informative: “Domestic campaign” and “Co-investment” are positive, while “Investment term” is negative; “Investment capital” is also negative, contrary to prior expectations. The results are robust to controls for the campaign sector and to alternative specifications (probit; OLS on achievement rate). Overall, investors in Japan’s LBCF appear to rely on diagnostic rather than peripheral signals, indicating financially literate, rational decision-making. Full article

This study investigates the dynamic relationship between key macroeconomic indicators, specifically inflation (CPI), the Federal Funds Rate, GDP growth, unemployment, and money supply, and U.S. stock market returns, represented by the S&P 500 index, over the period January 2015 to June 2025. The objective is to understand how inflation and monetary policy affect market performance in both the short and long run. Using an Autoregressive Distributed Lag (ARDL) modeling framework and Error Correction Model (ECM), the study examines monthly S&P 500 returns alongside macroeconomic variables, accounting for lagged effects and potential cointegration. The model captures both immediate and delayed impacts, employing the Bounds Testing approach to confirm long-run equilibrium relationships. Results show significant mean-reversion in stock returns, a delayed negative impact of inflation and interest rate increases, and a positive contemporaneous response to GDP growth. Unemployment exhibits a counterintuitive positive effect on returns, suggesting forward-looking investor expectations. The money supply also positively influences equity prices, supporting liquidity-based asset pricing theories. This paper provides updated empirical evidence on macro-finance linkages and highlights the complex interplay of monetary policy, inflation, and market expectations in shaping U.S. equity returns. Full article

This study proposes a novel approach to improve the reliability of trading signals for gold market prediction by integrating technical analysis indicators, Moving Averages (MAs), MACD, and Ichimoku Cloud, with a Particle Swarm-Optimized Extreme Learning Machine (PSO-ELM). Traditional time-series models often fail to capture the complex, non-linear dynamics of financial markets, whereas technical indicators combined with machine learning enhance predictive accuracy. Using daily gold prices from January–October 2020, the PSO-ELM model demonstrated superior performance in filtering false signals, achieving high precision, recall, and overall accuracy. The results highlight the effectiveness of combining technical analysis with machine learning for robust signal validation, providing a practical framework for traders and investors. While focused on gold, this methodology can be extended to other financial assets and market conditions. The integration of machine learning and blockchain enhances both predictive reliability and operational trust, offering traders, investors, and institutions a robust framework for decision support in dynamic financial environments. Full article

iFintech is termed as an Islamic alternative banking and financial services approach to that of existing, Fintech digital, Western democracies banking and financial systems. This Pakistan Islamic digital banking and financial services technologies (iFintech) study engages a qualitative NVivo study, and a quantitative covariance based structural equation modelling (CB-SEM) study to assess how young, tech savvy, capital city respondents likely approach their readiness to adopt iFintech. Study data engages qualitative assessments and quantitative framework modelling. Research findings show a competencies and capabilities framework enlists three major pathways (economic worth, social acceptance, plus technical transfer associated risks) that can influence iFintech adoption readiness. This empirical study presents a new, robust, iFintech adoption readiness approach which predominantly Islamic countries like Pakistan may choose to consider when encouraging their young, tech savvy, capital city residents towards adopting digital banking and financial services within their nation. Full article

Objective: This study investigates how artificial intelligence (AI) research relates to firm value, focusing on dominant thematic trends, theoretical foundations, and global collaboration patterns. Methods: A PRISMA-guided systematic review was conducted on 219 peer-reviewed articles published between 2013 and May 2025 in the Web of Science Social Sciences Citation Index. Bibliometric techniques, including co-word, co-citation, and collaboration network analyses, were performed using the bibliometrix (version 4.2.3) in R (version 4.4.2) package to map key concepts, intellectual structures, and international research partnerships. Results: The literature is primarily grounded in strategic management theories such as the resource-based view (RBV) and dynamic capabilities. Emerging research streams emphasize digital transformation, big data analytics, and decision support systems. Frequently co-occurring terms include “firm performance,” “artificial intelligence,” “dynamic capabilities,” “information technology,” and “decision-making.” Collaboration mapping highlights the United States, United Kingdom, and China as leading hubs, with increasing contributions from emerging economies such as India, Malaysia, and Saudi Arabia. The alignment between co-word and co-citation structures reflects a shift from foundational theory to applied AI capabilities in firm-value creation. Implications: By integrating a systematic review with advanced bibliometric and science-mapping methods, this work establishes a structured foundation for theory development, empirical testing, and policy formulation in AI-driven business landscapes. Full article

Large language models have expanded their application from traditional tasks in natural language processing to several domains of science, technology, engineering, and mathematics. This research studies the potential of these models for financial “nowcasting”–real-time forecasting (of the recent past) for cryptocurrency market conditions. Further, the research benchmarks capabilities of five state-of-the-art decoder-only models, gpt-4.1 (OpenAI), gemini-2.5-pro (Google), claude-3-opus-20240229 (Anthropic), deepseek-reasoner (DeepSeek), and grok-4 (xAI) across 12 major crypto-assets around the world. Using minute-resolution history of a day in USD for the stocks, gemini-2.5-pro emerges as a consistent leader in forecasting (except for a few assets). The stablecoins exhibit minimal deviation across all models, justifying the “nowcast strength” in low-volatility environments, although they are not able to perform well for the highly erratic assets. Additionally, since large language models have been known to better their performance when executed for a higher number of passes, the experimentations were conducted for two passes (Pass@1 and Pass@2), and the respective nowcast errors are found to be reduced by $1.2156\%$ (on average). Full article

Quantum technology is significantly transforming businesses, organisations, and information systems. It will have a significant impact on accounting and finance, particularly in the context of cybersecurity. It presents both opportunities and risks in maintaining confidentiality and protecting financial data. This study aims to demonstrate the application of quantum technologies in accounting cybersecurity, utilising quantum algorithms and QKD to overcome the limitations of classical computing. The literature review emphasises the vulnerabilities of current accounting cybersecurity to quantum attacks and highlights the necessity for quantum-resistant cryptographic mechanisms. It discusses the risks related to traditional encryption methods within the context of quantum capabilities. This research enhances understanding of how quantum computing can revolutionise accounting cybersecurity by advancing quantum-resistant algorithms and implementing QKD in accounting systems. This study employs the PSALSAR systematic review methodology to ensure thoroughness and rigour. The analysis shows that quantum computing pushes encryption techniques beyond classical limits. Using quantum technologies in accounting reduces data breaches and unauthorised access. This study concludes that quantum-resistant algorithms and quantum key distribution (QKD) are crucial for securing the future of accounting and finance systems. Full article