Artificial Intelligence Applications in Financial Technology, 2nd Edition

Topic Information

Dear Colleagues,

This is the second edition of the previous successful Topic “Artificial Intelligence Applications in Financial Technology”. Financial technology (fintech) refers to the use of information technology to simplify, improve, reshape, and automate financial processes and services for businesses and customers. In the financial world, many processes and services rely heavily on humans, resulting in mistakes, inefficiency, compliance issues, and penalty fines. They may involve document handling and communications between agents and customers, supervisors and subordinates, and institutions and regulators. Fintech allows various financial institutions to manipulate many of these processes and services with electronic devices, which can work 24/7 at the same standard more efficiently. In particular, artificial intelligence (AI) equips machines with human cognitive skills so that certain tasks can now be automated, especially in relation to image, natural language, and speech. For example, we can covert handwritten documents or printouts into electronic formats for further analysis. Natural language processing facilitates the extraction of useful information in a piece of text, and speech recognition allows us to analyze a conversation. Fintech has become an essential tool to the global BFSI (banking, financial services, and insurance) industry, and it has branched out into specific disciplines, e.g., regtech for the management of regulatory processes, suptech for regulatory supervision and oversight, and insurtech for new insurance product and solution designs. This Topic therefore seeks to contribute to the agenda of AI applications in fintech through enhanced scientific and multidisciplinary knowledge to improve performance and deployment by bringing focus to various AI technologies suitable for BFSI in order to meet technical, social, and economic goals. We are particularly interested in investigating how AI technologies contribute to the financial industry and vice versa. We therefore invite you to submit papers on innovative technical developments, reviews, and analytical as well as assessment papers from different disciplines which are relevant to the integration of AI and fintech. Topics of interest for publication include, but are not limited to, the following:

• Chatbots in fintech;
• Natural language processing;
• Speech cognition and synthesis;
• Image recognition;
• AI-powered personalized banking;
• Complex system applications (including ESG);
• User behavior analysis;
• Fraud detection;
• Anti-money laundering;
• Consistent customer services;
• Cryptocurrency;
• Cybersecurity.

Prof. Dr. Albert Y.S. Lam
Prof. Dr. Andy Chun
Topic Editors

Keywords

Participating Journals

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
AI ai	6.5	7.3	2020	19.2 Days	CHF 1800	Submit
Big Data and Cognitive Computing BDCC	5.3	11.4	2017	23.1 Days	CHF 1800	Submit
FinTech fintech	2.8	7.5	2022	20.2 Days	CHF 1200	Submit
International Journal of Financial Studies ijfs	2.7	5.0	2013	19.7 Days	CHF 1800	Submit
Journal of Theoretical and Applied Electronic Commerce Research jtaer	4.5	7.1	2006	27.9 Days	CHF 1400	Submit
Risks risks	1.8	4.5	2013	20 Days	CHF 1800	Submit

Preprints.org is a multidisciplinary platform offering a preprint service designed to facilitate the early sharing of your research. It supports and empowers your research journey from the very beginning.

MDPI Topics is collaborating with Preprints.org and has established a direct connection between MDPI journals and the platform. Authors are encouraged to take advantage of this opportunity by posting their preprints at Preprints.org prior to publication:

1. Share your research immediately: disseminate your ideas prior to publication and establish priority for your work.
2. Safeguard your intellectual contribution: Protect your ideas with a time-stamped preprint that serves as proof of your research timeline.
3. Boost visibility and impact: Increase the reach and influence of your research by making it accessible to a global audience.
4. Gain early feedback: Receive valuable input and insights from peers before submitting to a journal.
5. Ensure broad indexing: Web of Science (Preprint Citation Index), Google Scholar, Crossref, SHARE, PrePubMed, Scilit and Europe PMC.

Related Topic

Published Papers (12 papers)

Order results

Content type Publication Date

Result details

Normal Extended Compact

Journals

All AI BDCC FinTech IJFS JTAER Risks

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

Error

Oops... you haven't selected anything for export.

Ok

clear

23 pages, 450 KB  

Open AccessArticle

Generative AI as an Investment Advisor: Same Client, Different Advice

by Nicolo Agliata and Tim Hasso

FinTech 2026, 5(2), 54; https://doi.org/10.3390/fintech5020054 - 11 Jun 2026

Viewed by 204

Abstract

Generative artificial intelligence (GAI) is increasingly embedded in personal finance, yet little is known about how models make recommendations using financial information and demographic cues. This study audits three frontier GAI models, GPT 5.5, Gemini 3.1 Pro, and Claude Opus 4.7, using a [...] Read more.

Generative artificial intelligence (GAI) is increasingly embedded in personal finance, yet little is known about how models make recommendations using financial information and demographic cues. This study audits three frontier GAI models, GPT 5.5, Gemini 3.1 Pro, and Claude Opus 4.7, using a conjoint experiment in which each model evaluated the same hypothetical investor profiles and selected among standardized conservative, balanced, and aggressive portfolios. Investor profiles systematically varied attributes, including risk tolerance, time horizon, goal type, income, and age, gender, ethnicity, marital status, and employment type. Ordered logistic regressions and matched-profile comparisons show that all three models base recommendations primarily on financial attributes, especially risk tolerance and time horizon. Age and marital status shift recommendations towards conservatism in all models, conversely only Claude conditions on gender and employment type. Ethnicity exerts no detectable influence on the recommendations of ChatGPT or Claude, but is a small, statistically significant predictor for Gemini, with non-White profiles receiving slightly more conservative recommendations than otherwise identical White profiles. Overall, we find that the models are not interchangeable: they differ significantly in overall risk appetite and in how they translate risk tolerance, time horizon, goal type, and age into portfolio choices, with economically meaningful differences in predicted recommendations for identical clients. These findings suggest that contemporary GAI investment advice is driven mainly by financially relevant attributes, but that demographic sensitivity may appear in model-specific and statistically nuanced ways, alongside a distinct form of platform risk arising from model-specific advisory logic. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

40 pages, 1511 KB  

Open AccessArticle

Quantum Hyperbolic Deep Learning for Foreign-Exchange Trading: A Hybrid Reinforcement-Learning Pipeline over Attractor-Aware Magnet-Price Manifolds

by Francesco Rundo

Big Data Cogn. Comput. 2026, 10(6), 191; https://doi.org/10.3390/bdcc10060191 - 11 Jun 2026

Viewed by 376

Abstract

Foreign-exchange decisions rest on hierarchically organized evidence whose latent structure is inadequately captured by Euclidean representations. Reinforcement-learning agents trained on flat embeddings inherit stability guarantees that do not transfer to the manifold supporting the latent state. We address both limitations through a hybrid [...] Read more.

Foreign-exchange decisions rest on hierarchically organized evidence whose latent structure is inadequately captured by Euclidean representations. Reinforcement-learning agents trained on flat embeddings inherit stability guarantees that do not transfer to the manifold supporting the latent state. We address both limitations through a hybrid architecture in which a schema-constrained structured chain-of-thought is embedded into a Poincaré ball, transported to a qubit register via angle encoding, and processed by an L-layer hardware-efficient variational ansatz on a state-vector backend. The circuit exposes two read-outs to the policy, namely, a scalar Pauli-Z observable and a projected quantum kernel inducing a fidelity-based similarity over magnet-price attractors, the latter identified via kernel-weighted recurrence density and finite-time Lyapunov statistics. The Lipschitz constraint on the action-value function is lifted from the hyperbolic geodesic distance to a joint metric on ${\mathbb{B}}_{\kappa }^n\times \mathbb{P}\left(\mathcal{H}\right)$. A stability theorem yields an explicit bound depending on the read-out operator norm, on the depth–width product of the ansatz, and on the curvature–Hilbert balance. The pipeline is evaluated on nine major FX crosses over a 2015–2025 out-of-sample window, with rolling-origin walk-forward retraining and broker-published transaction costs. The system attains $2.55\%$ pair-averaged non-compounded monthly P&L and $8.83\%$ maximum drawdown, with Sharpe $1.78$, Calmar $3.43$, and Probabilistic Sharpe Ratio exceeding $0.95$ on every cross. The gain remains significant under a deflated-Sharpe-ratio test with $N_{\mathrm{trials}}=42$ correction. Block-wise ablations exhibit strictly monotone degradation: removing the projected kernel costs $-4.15$ p.p. on annualized P&L, the joint Lipschitz penalty $-6.42$ p.p., the attractor module $-7.64$ p.p., and the hyperbolic embedding $-8.40$ p.p. The quantum block thereby instantiates a structurally non-classical, geometry-aware regularizer identifiable through ablation rather than asymptotically advantageous. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

26 pages, 1332 KB  

Open AccessArticle

An Explainable Hybrid AI Framework for Real-Time Point-of-Sale Credit Scoring

by Gulnaz Zakariya, Aiman Moldagulova and Nor’ashikin Ali

AI 2026, 7(6), 211; https://doi.org/10.3390/ai7060211 - 9 Jun 2026

Viewed by 415

Abstract

Point-of-sale (POS) consumer credit represents the most rapidly expanding retail-lending channel within the emerging Eurasian markets, necessitating a stringent operational framework for the underwriting model: the decision must be rendered within a mere few hundred milliseconds during the in-store checkout process, while the [...] Read more.

Point-of-sale (POS) consumer credit represents the most rapidly expanding retail-lending channel within the emerging Eurasian markets, necessitating a stringent operational framework for the underwriting model: the decision must be rendered within a mere few hundred milliseconds during the in-store checkout process, while the inputs are constrained to what the application XML is capable of conveying. This research endeavors to develop, internally validate, and operationally delineate a hybrid, explainable artificial intelligence framework aimed at POS credit scoring within the production portfolio of Kazakhstan’s largest second-tier bank. The architectural framework is delineated along two orthogonal dimensions—client tenure and decision-making channel—resulting in the formulation of three distinct production models: two transparent Weight of Evidence–Logistic Regression scorecards tailored for the real-time channel, and one isotonically-calibrated stacked ensemble (comprising LightGBM, CatBoost, and a three-layer neural network) designated for the batch channel. The selection of hyperparameters was conducted utilising Bayesian optimization within the context of stratified five-fold cross-validation. The digital scorecards achieve an area under the receiver operating characteristic curve (AUROC) of 0.847 and 0.835, whereas the offline ensemble enhances performance to an AUROC of 0.918, accompanied by a Kolmogorov–Smirnov statistic of 0.682 and a Gini coefficient of 0.836. The population stability indices persist below the threshold of 0.07, while isotonic recalibration effectively reduces the Brier score by 18%. Furthermore, an extensive examination of fairness demonstrates variations in approval rates within a margin of ±1.2 percentage points—and equalised-odds gaps below 1.5 percentage points in the true-positive rate and 0.7 percentage points in the false-positive rate—across multiple demographic factors such as gender, age, and distinctions between urban and rural classifications, thus establishing an artificial intelligence framework that is both regulatorily compliant and interpretable, aligning with the directives set forth by the Agency of the Republic of Kazakhstan for Regulation and Development of the Financial Market. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

24 pages, 6161 KB  

Open AccessArticle

Just-in-Time Historical State Reconstruction for Low-Latency Financial Trading with Large Language Models

by Dong Hoang Van, Md Monjurul Karim and Qiang Qu

AI 2026, 7(4), 117; https://doi.org/10.3390/ai7040117 - 27 Mar 2026

Viewed by 2970

Abstract

This paper introduces Historical State Reconstruction, a novel framework for low-latency financial decision-making using Large Language Models. While agentic systems have demonstrated potential in synthesizing complex financial narratives, they typically rely on Retrieval-Augmented Generation or memory-based architectures. These paradigms introduce significant latency and [...] Read more.

This paper introduces Historical State Reconstruction, a novel framework for low-latency financial decision-making using Large Language Models. While agentic systems have demonstrated potential in synthesizing complex financial narratives, they typically rely on Retrieval-Augmented Generation or memory-based architectures. These paradigms introduce significant latency and risk look-ahead bias during real-time inference, rendering them unsuitable for high-frequency trading environments where milliseconds determine profitability. This proposed framework resolves this bottleneck by decoupling the heavy computational cost of context acquisition from the latency-sensitive critical path of decision-making. We propose a system that proactively compiles unstructured regulatory filings (10-K, 10-Q, 8-K) into a structured, bitemporal database. By pre-computing complex state facets, such as financial health ratios, governance structures, and insider trading signals offline, the system allows trading agents to “time travel” to a reconstructed state at any historical moment t with $O(1)$ snapshot retrieval plus $O(k)$ delta application complexity. We implement this approach on the top 50 companies in the S&P 500 ranked by market capitalization, processing over 12,000 filings to demonstrate a pipeline that transforms high-dimensional financial narratives into compact, prompt-ready context. Our evaluation shows that the system reduces context retrieval latency by over 97% compared to traditional baselines while achieving a 300:1 compression ratio for financial health data. Furthermore, the bitemporal architecture guarantees strict temporal integrity, eliminating the risk of data leakage in backtesting and satisfying the reproducibility requirements of regulatory frameworks like SR 11-7. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Graphical abstract

21 pages, 2801 KB  

Open AccessReview

Financial Education in the Age of Artificial Intelligence: A Systematic Review with Text Mining and Natural Language Processing

by Eveling Sussety Balcazar-Paiva, Alexander Fernando Haro-Sarango and Juan Amilcar Villanueva-Calderón

Int. J. Financial Stud. 2026, 14(3), 76; https://doi.org/10.3390/ijfs14030076 - 16 Mar 2026

Viewed by 1936

Abstract

This article develops a rigorous and reproducible systematic review of the integration of artificial intelligence (AI) in financial education during the period 2020–2025, structured in accordance with -5.3-PRISMA and explicitly oriented toward detecting narrative and perception. The search was conducted in three complementary [...] Read more.

This article develops a rigorous and reproducible systematic review of the integration of artificial intelligence (AI) in financial education during the period 2020–2025, structured in accordance with -5.3-PRISMA and explicitly oriented toward detecting narrative and perception. The search was conducted in three complementary databases (Scopus, ScienceDirect, and Taylor & Francis), using search strings equivalent to those of the platform and a selection workflow that begins with 388 records and culminates in 50 included studies, prompting a narrative synthesis given the methodological heterogeneity. From a methodological contribution perspective, the study combines bibliometric mapping with text mining and an NLP process that triangulates sentiment using lexicon-based approaches (VADER, TextBlob) and a multilingual transformer model (XLM-RoBERTa), producing continuous indicators (sentiment index) and reproducible research artifacts. The results position AI as an integrative nexus linking financial literacy, decision-making, sustainability, and language technologies (including ChatGPT-5.3.), highlighting its potential for personalization, virtual tutoring, and immediate gains in comprehension and motivation; however, evidence of sustained behavioral change remains nascent. Critical gaps remain, such as a shortage of longitudinal/controlled studies, a lack of standardized metrics, limited transparency and validation of models, and constraints in terms of geographic and cultural diversity, while privacy, fairness, and algorithmic bias emerge as structural conditions for responsible adoption. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

20 pages, 3196 KB  

Open AccessArticle

Semantic Firewalls with Online Ensemble Learning for Secure Agentic RAG Systems in Financial Chatbots

by Victor Castro-Maldonado, Marco A. Aceves-Fernández, Luis R. García-Noguez and Jesús C. Pedraza-Ortega

AI 2026, 7(3), 80; https://doi.org/10.3390/ai7030080 - 27 Feb 2026

Viewed by 1276

Abstract

The RAG agentic architecture has demonstrated its ability to transform large language models (LLMs) into agents capable of planning, reasoning, and executing subtasks using external tools or APIs. In the financial sector, one of the main priorities when implementing new technologies—especially in systems [...] Read more.

The RAG agentic architecture has demonstrated its ability to transform large language models (LLMs) into agents capable of planning, reasoning, and executing subtasks using external tools or APIs. In the financial sector, one of the main priorities when implementing new technologies—especially in systems like chatbots—is the protection of customer data and the need to maintain customer trust, making the challenges significant. This research presents a robust banking chatbot system that integrates RAG agentic architecture with specialized financial components, setting a new standard in the digital banking sector by prioritizing security, transparency, and functionality. The contributions of this work include the implementation of RAG agentic reasoning and self-correction financial components, and, primarily, the empirical study of the impact of a semantic firewall with online learning in financial RAG agentic systems, evaluated using public benchmarks and standard ranking metrics. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

23 pages, 1951 KB  

Open AccessArticle

LFTD: Transformer-Enhanced Diffusion Model for Realistic Financial Time-Series Data Generation

by Gyumun Choi, Donghyeon Jo, Wonho Song, Hyungjong Na and Hyungjoon Kim

AI 2026, 7(2), 60; https://doi.org/10.3390/ai7020060 - 5 Feb 2026

Viewed by 1539

Abstract

Firm-level financial statement data form multivariate annual time series with strong cross-variable dependencies and temporal dynamics, yet publicly available panels are often short and incomplete, limiting the generalization of predictive models. We present Latent Financial Time-Series Diffusion (LFTD), a structure-aware augmentation framework that [...] Read more.

Firm-level financial statement data form multivariate annual time series with strong cross-variable dependencies and temporal dynamics, yet publicly available panels are often short and incomplete, limiting the generalization of predictive models. We present Latent Financial Time-Series Diffusion (LFTD), a structure-aware augmentation framework that synthesizes realistic firm-level financial time series in a compact latent space. LFTD first learns information-preserving representations with a dual encoder: an FT-Transformer that captures within-year interactions across financial variables and a Time Series Transformer (TST) that models long-horizon evolution across years. On this latent sequence, we train a Transformer-based denoising diffusion model whose reverse process is FiLM-conditioned on the diffusion step as well as year, firm identity, and firm age, enabling controllable generation aligned with firm- and time-specific context. A TST-based Cross-Decoder then reconstructs continuous and binary financial variables for each year. Empirical evaluation on Korean listed-firm data from 2011 to 2023 shows that augmenting training sets with LFTD-generated samples consistently improves firm-value prediction for market-to-book and Tobin’s Q under both static (same-year) and dynamic ($\tau$ → $\tau +1$) forecasting settings and outperforms conventional generative augmentation baselines and ablated variants. These results suggest that domain-conditioned latent diffusion is a practical route to reliable augmentation for firm-level financial time series. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

31 pages, 847 KB  

Open AccessArticle

Exploring the Customer Experience Regarding AI-Powered Fintech Chatbots in Terms of SOR Theory

by Selim Çam, Murat Fatih Tuna and Talha Bayır

J. Theor. Appl. Electron. Commer. Res. 2026, 21(2), 49; https://doi.org/10.3390/jtaer21020049 - 2 Feb 2026

Cited by 1 | Viewed by 2586

Abstract

This study examines how the design and interaction features of AI-powered fintech chatbots shape the customer experience of Generation Z users by integrating the Stimulus-Organism-Response framework with dual-process perspectives. Two cross-sectional surveys were conducted in Türkiye. Study 1 (n = 166) examines the [...] Read more.

This study examines how the design and interaction features of AI-powered fintech chatbots shape the customer experience of Generation Z users by integrating the Stimulus-Organism-Response framework with dual-process perspectives. Two cross-sectional surveys were conducted in Türkiye. Study 1 (n = 166) examines the effect of social presence, interactivity, visual appeal, design originality, and usability on perceived competence and perceived warmth, which, in turn, shape the customer experience. Social presence and design originality significantly increased perceived competence (β = 0.47, p < 0.001), while visual appeal enhanced perceived warmth (β = 0.32, p < 0.001). Together, competence and warmth explained a substantial proportion of customer experience (R² ≈ 0.60). Usability and interactivity showed no significant effects. Study 2 (n = 195) replicated these findings with trained users and introduced task complexity as a moderator. Under high task complexity, usability and interactivity became significant predictors of competence, which emerged as the primary driver of customer experience, whereas the influence of warmth diminished. Non-normal data distributions justified the use of Partial Least Squares Structural Equation Modeling. Overall, the findings suggest a shift from heuristic to systematic processing as fintech tasks become more complex, highlighting the growing importance of competence-based evaluations in fintech chatbot interactions. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

25 pages, 458 KB  

Open AccessArticle

Shifting Perceptions and Behaviors: The Impact of Digitalization on Banking Services

by Alina Elena Ionașcu, Vlad I. Bocanet, Nicoleta Asaloș, Cristina Mihaela Lazăr, Elena Cerasela Spătariu, Corina Aurora Barbu and Dorinela Nancu

J. Theor. Appl. Electron. Commer. Res. 2025, 20(4), 295; https://doi.org/10.3390/jtaer20040295 - 1 Nov 2025

Cited by 2 | Viewed by 2992

Abstract

The rapid digitalization of banking services has transformed consumer interactions, necessitating a deeper understanding of the factors influencing online banking adoption. This research investigates the factors influencing consumer adoption in a country undergoing rapid digital transformation but still facing gaps in digital skills [...] Read more.

The rapid digitalization of banking services has transformed consumer interactions, necessitating a deeper understanding of the factors influencing online banking adoption. This research investigates the factors influencing consumer adoption in a country undergoing rapid digital transformation but still facing gaps in digital skills and infrastructure—Romania. The objective of the study is to analyze how key variables such as ease of use, security, speed, usefulness, and social pressure influence online banking behavior of Romanian consumers, especially the most digitally engaged ones. The study utilizes a multi-method empirical approach, hypothesis testing, binary logistic regression for prediction modeling, and segmentation analysis to offer a comprehensive view of customer behavior. The findings identify essential adoption drivers and separate customer profiles, providing useful information for financial organizations aiming to enhance their digital strategy. Perceived ease of use and perceived security are primary factors influencing adoption; nevertheless, decision tree analysis indicates that speed and usefulness have a more significant impact than logistic regression implies, but social pressure unexpectedly serves as an impediment. These results highlight the necessity for banks to customize their digital services, harmonizing security and user-friendliness with improved efficiency and usefulness to promote broader adoption in emerging digital economies like Romania. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

21 pages, 872 KB  

Open AccessArticle

The Impact of Central Bank Digital Currencies (CBDCs) on Global Financial Systems in the G20 Country GVAR Approach

by Nesrine Gafsi

FinTech 2025, 4(3), 35; https://doi.org/10.3390/fintech4030035 - 24 Jul 2025

Cited by 8 | Viewed by 12264

Abstract

This paper considers the impact of Central Bank Digital Currencies (CBDCs) on the world’s financial systems with a special emphasis on G20 economies. Using quarterly macro-financial data for the period of 2000 to 2024, collected from the IMF, BIS, World Bank, and Atlantic [...] Read more.

This paper considers the impact of Central Bank Digital Currencies (CBDCs) on the world’s financial systems with a special emphasis on G20 economies. Using quarterly macro-financial data for the period of 2000 to 2024, collected from the IMF, BIS, World Bank, and Atlantic Council, a Global Vector Autoregression (GVAR) model is applied to 20 G20 countries. The results reveal significant heterogeneity across economies: CBDC shocks intensify emerging market financial instability (e.g., India, Brazil), while more digitally advanced countries (e.g., UK, Japan) experience stabilization. Retail CBDCs increase disintermediation risks in more fragile banking systems, while wholesale CBDCs improve cross-border liquidity. This article contributes to the literature by providing the first GVAR-based estimation of CBDC spillovers globally. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

25 pages, 1628 KB  

Open AccessArticle

Robust AI for Financial Fraud Detection in the GCC: A Hybrid Framework for Imbalance, Drift, and Adversarial Threats

by Khaleel Ibrahim Al-Daoud and Ibrahim A. Abu-AlSondos

J. Theor. Appl. Electron. Commer. Res. 2025, 20(2), 121; https://doi.org/10.3390/jtaer20020121 - 1 Jun 2025

Cited by 34 | Viewed by 6578

Abstract

The rising complexity of financial fraud in highly digitalized regions such as the Gulf Cooperation Council (GCC) poses challenging issues owing to class imbalance, adversarial attacks, concept drift, and explainability requirements. This paper suggests a hybrid machine-learning framework (HMLF) that incorporates SMOTEBoost and [...] Read more.

The rising complexity of financial fraud in highly digitalized regions such as the Gulf Cooperation Council (GCC) poses challenging issues owing to class imbalance, adversarial attacks, concept drift, and explainability requirements. This paper suggests a hybrid machine-learning framework (HMLF) that incorporates SMOTEBoost and cost-sensitive learning to address imbalances, adversarial training and FraudGAN to ensure robustness, DDM and ADWIN to achieve adaptive learning, and SHAP, LIME, and human-in-the-loop (HITL) analysis to ensure explainability. Employing real transaction data from the GCC banks, the framework is tested through a design science research approach. Experiments illustrate significant gains in fraud recall (from 35% to 85%), adversarial robustness (attack success rate decreased from 35% to 5%), and drift recovery (within 24 h), while retaining operational latency below 150 milliseconds. This paper substantiates that incorporating technical resilience with institutional constraints offers an auditable, scalable, and regulation-compliant solution for detecting fraud in high-risk financial contexts. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

27 pages, 4436 KB  

Open AccessArticle

Leveraging Large Language Models for Sentiment Analysis and Investment Strategy Development in Financial Markets

by Yejoon Mun and Namhyoung Kim

J. Theor. Appl. Electron. Commer. Res. 2025, 20(2), 77; https://doi.org/10.3390/jtaer20020077 - 20 Apr 2025

Cited by 7 | Viewed by 13114

Abstract

This study investigates the application of large language models (LLMs) in sentiment analysis of financial news and their use in developing effective investment strategies. We conducted sentiment analysis on news articles related to the top 30 companies listed on Nasdaq using both discriminative [...] Read more.

This study investigates the application of large language models (LLMs) in sentiment analysis of financial news and their use in developing effective investment strategies. We conducted sentiment analysis on news articles related to the top 30 companies listed on Nasdaq using both discriminative models such as BERT and FinBERT, and generative models including Llama 3.1, Mistral, and Gemma 2. To enhance the robustness of the analysis, advanced prompting techniques—such as Chain of Thought (CoT), Super In-Context Learning (SuperICL), and Bootstrapping—were applied to generative LLMs. The results demonstrate that long strategies generally yield superior portfolio performance compared to short and long–short strategies. Notably, generative LLMs outperformed discriminative models in this context. We also found that the application of SuperICL to generative LLMs led to significant performance improvements, with further enhancements noted when both SuperICL and Bootstrapping were applied together. These findings highlight the profitability and stability of the proposed approach. Additionally, this study examines the explainability of LLMs by identifying critical data considerations and potential risks associated with their use. The research highlights the potential of integrating LLMs into financial strategy development to provide a data-driven foundation for informed decision-making in financial markets. Full article

(This article belongs to the Topic Artificial Intelligence Applications in Financial Technology, 2nd Edition)

►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less

Select all

Export citation of selected articles as:

Plain Text BibTeX BibTeX (without abstracts) Endnote Endnote (without abstracts) Tab-delimited RIS

 

Error

Oops... you haven't selected anything for export.

Ok

clear

Displaying articles 1-12