Blockchain Papers

Reza Javadzadeh

No abstract is available for this record.

Reza Akbar Ramadhan, Ratnawati Raflis

This study aims to analyze the comparative performance of Cryptocurrency Bitcoin, Stocks, and Gold as investment instruments using performance measurement variables including the Sharpe, Treynor, Jensen, and Sortino ratios. This research employs a descriptive quantitative approach. The population consists of monthly closing prices of Bitcoin, IDX30 stocks, and Gold. The sampling technique used is saturated sampling, resulting in 60 data points for each investment instrument—Bitcoin, IDX30 stocks, and Gold—during the period from January 1, 2020 to December 31, 2024.The analytical method applied is comparative analysis using secondary data. The data were initially calculated using Microsoft Excel and subsequently processed statistically using SPSS through the Kruskal–Wallis test. The results indicate significant differences among Bitcoin, IDX30 stocks, and Gold when investment performance is assessed using the Sharpe, Treynor, Jensen, and Sortino indices.Based on the Kruskal–Wallis test, Gold demonstrates the best performance according to the Sharpe and Jensen indices, IDX30 stocks perform best according to the Treynor index, and Bitcoin shows the best performance according to the Sortino index. However, based on the highest overall average return value, Cryptocurrency Bitcoin outperforms the other instruments. Therefore, it can be concluded that the best alternative investment is Cryptocurrency Bitcoin. Penelitian ini bertujuan untuk menganalisis perbandingan kinerja Cryptocurrency Bitcoin, Saham, dan Emas sebagai instrumen investasi menggunakan variabel pengukuran kinerja Sharpe, Treynor, jensen, dan Sortino. Jenis penelitian merupakan kuantitatif Deskriptif. Populasi yang digunakan merupakan harga penutupan bulanan dari Bitcoin, IDX30, dan Emas. Teknik pemilihan sampel adalah sampel jenuh yang berjumlah 60 data untuk masing-masing instrumen investasi Bitcoin, Saham IDX30, dan Emas selama periode 1 januari 2020 – 31 Desember 2024. Metode analisis yang digunakan adalah metode komperatif dan menggunakan data sekunder. Data dihitung terlebih dahulu dengan menggunakan program Microsoft Excel kemudian diolah secara statistik menggunakan aplikasi SPSS yaitu Uji Kruskall-Wallis. Hasil penelitian menunjukkan bahwa terdapat perbedaan yang signifikan antara Bitcoin, Saham IDX30, dan Emas jika kinerja investasi dilihat dari Indeks Sharpe, Treynor, Jensen, dan Sortino. Berdasarkan uji Kruskal-Wallis, investasi terbaik menurut indeks Sharpe dan Jensen , adalah Emas, sedangkan menurut Indeks Teynor Saham IDX30, dan menurut Indeks Sortino adalah Cryptocurrency Bitcoin. Sedangkan dengan nilai jumlah rata-rata terbaik adalah Cryptocurrency Bitcoin. Sehingga dapat disimpulkan bahwa alternatif investasi terbaik adalah Cryptocurrency Bitcoin.

Matloob Khushi

Abstract Financial time-series forecasting lies between AI and market microstructure, but most studies optimise generic error metrics instead of risk-adjusted economic value under realistic frictions. Unlike NLP and vision, the field lacks a shared, reviewer-enforced standard for data handling and evaluation, leading to persistent problems such as data leakage, backtest overfitting and metric-chasing on RMSE/MAE. This paper introduces QFRS a novel, enforceable by reviewers and editors, seven-standard framework and checklist for evaluating and reporting financial asset forecasting and trading claims. QFRS covers quantitative studies on equities (stocks), forex, cryptocurrencies, rates, derivatives (futures, forwards, options, swaps), energy prices, and commodities (gold, oil and silver) and other asset classes. The seven standards specify an end-to-end experimental pipeline, covering (i) dataset construction, (ii) labelling, (iii) point-in-time feature engineering, (iv) leakage-free scaling or normalisation, (v) time-respecting data splits, (vi) evaluation metrics and (vii) cost and slippage-aware backtesting with explicit execution assumptions and decision rules mapping predictions to positions. To validate the standard’s diagnostic value, a compliance audit of Scopus-indexed forex forecasting papers published in 2025 is presented. None of these papers achieved full compliance across all seven standards, with economic backtesting (12.2%) and causal scaling (31.7%) recorded the lowest pass rates. QFRS underpins a public state-of-the-art leaderboard, ensuring that only studies satisfying these standards are ranked, with the goal of shifting the literature from opaque, error-metric-driven results to transparent, economically meaningful and comparable benchmarks. The accompanying leaderboard is available and updated regularly at http://mkhushi.github.io .

Haris Mehmood, Ahmad Zafar

This paper introduces the Dynamic External Memory LSTM (DEM-LSTM), a novel deep neural architecture designed to address the hidden state information bottleneck and temporal context decay inherent to standard LSTMs in financial time-series forecasting. By decoupling sequence processing from persistent state storage via an addressable external memory matrix ($M_t$), DEM-LSTM dynamically reads, erases, and updates market context across long sequences without corrupting internal hidden representations. Evaluated across four distinct asset classes—Foreign Exchange (EUR/USD), Commodities (XAU/USD and USOIL), and Cryptocurrencies (BTC/USD)—DEM-LSTM consistently outperforms standard LSTM baselines across all metrics, achieving up to a 41.4% reduction in RMSE on Gold spot prices while maintaining superior stability across high-volatility market regimes.

Arpita Paul

Abstract: The evolution of monetary systems has transformed human civilization from simple barter exchanges to sophisticated digital financial ecosystems powered by blockchain technology. This review examines how barter systems evolved into con-temporary virtual currencies across history and assesses how cryptocurrencies fit into the circular economy. The study explores the shortcomings of conventional monetary systems and looks at how decentralized, transparent, and effective forms of economic transaction have been made possible by digital currencies like Bitcoin. Additionally, the study examines how blockchain technology might be used to support waste reduction, sustainability, resource efficiency, and transparent supply chain management. The study also assesses the difficulties posed by virtual currencies, such as market volatility, cybersecurity threats, regulatory ambiguity, and environmental issues pertaining to cryptocurrency mining. The review identifies significant research gaps and future prospects for incorporating virtual currencies into sustainable economic systems by synthesizing the body of existing work. The results indicate that through openness, decentralization, and technological innovation, blockchain-enabled financial systems have a great deal of potential to promote circular economy goals. Keywords: Virtual Currency, Cryptocurrency, Bitcoin, Blockchain, Circular Economy, Sustainable Finance, Digital Economy, Decentralization, Green Finance, FinTech, Supply Chain Management

George Thomas Sofras, Ourania Theodosiadou, Theodora Tsikrika, Stefanos Vrochidis · 5 authors

The increasing use of cryptocurrencies, especially Bitcoin (BTC), has created new challenges for financial investigation. Although blockchain transactions are publicly accessible, the pseudo-anonymous nature of cryptocurrency networks can facilitate illicit financial activity. This work explores anomaly detection in the Bitcoin network using a semi-supervised Long Short-Term Memory Autoencoder (LSTM-AE). The focus is on the analysis of wallet activity over time in order to capture temporal behavioral patterns that may be related to illicit activities. Experiments are conducted on the Elliptic++ dataset. The model is trained exclusively on licit behaviour and the results indicate that the proposed formulation is able to retrieve a large proportion of illicit wallets despite the highly imbalanced setting.

Zeba Kousar, L Mallesha

Cryptocurrencies have emerged as a prominent asset class characterized by rapid price fluctuations, growing institutional participation, and continuing debate over whether their price movements are random or predictable. This study examines the randomness and weak-form market efficiency of the top ten cryptocurrencies by market capitalization—Bitcoin, Ethereum, Tether, Binance Coin, XRP, USD Coin, Solana, TRON, Dogecoin, and Hype liquid—using daily closing price data from April 2016 to March 2026 (subject to data availability for each coin). Daily log returns were tested using Descriptive Statistics, the Jarque–Bera test of normality, the Wald–Wolfowitz Run Test, and the Autocorrelation Test. The results show that daily returns for all selected cryptocurrencies are non-normally distributed, exhibiting excess kurtosis and skewness. The Run Test results indicate that seven of the ten cryptocurrencies—Bitcoin, Ethereum, Tether, Binance Coin, XRP, USD Coin, and Dogecoin—do not follow a random walk, while Solana, TRON, and Hype liquid exhibit randomness consistent with weak-form efficiency. However, the Autocorrelation Test reveals strong positive serial correlation across all ten cryptocurrencies, indicating that the market falls short of weak-form efficiency. The study concludes that the cryptocurrency market provides mixed and largely inefficient evidence with respect to the Random Walk Hypothesis, implying that historical price information may retain some predictive value for investors.

Agon Bajgora, Andrea Kulakov, Faton Merovci

Existing autonomous trading systems rely on collaborative or single-agent analysis, lacking structured mechanisms for adversarial deliberation across opposing market perspectives. We propose Consensus-Gated Execution (CGX), a multi-agent architecture where specialized Bull and Bear agents engage in a three-round structured debate, with a Meta-Evaluator synthesizing their arguments to gate trade execution based on consensus strength. The system is evaluated through two complementary experiments: a 52-week aggregation study (2024) and a four-year multi-regime validation (2022–2025) across 417 biweekly sessions spanning bear, recovery, bull, and mixed market conditions. Trade signals are filtered using a tunable consensus threshold, allowing the system to balance trading frequency against signal quality. In the aggregation study, CGX achieves a Sharpe ratio of 1.90 with a maximum drawdown of 11.6%, representing a 3× improvement over trend following. In the multi-year evaluation, CGX reduces maximum drawdown by 85% and annualized volatility by 86%, with the Bear gate blocking 93% of sessions during the 2022 crash versus only 12% during the 2024 bull run. These results demonstrate that adversarial debate combined with consensus-based execution gating provides a principled framework for capital preservation across diverse market regimes.

Hongru He, Akihiro Fujihara

High-performance Byzantine Fault Tolerant (BFT) blockchains are designed to achieve high throughput and low latency, yet their observed block time distributions often reveal complex behaviors arising from networking, pipelining, and deployment heterogeneity. In this paper, we diagnose HotStuff-based high-performance BFT consensus by modeling block times through a quorum-based multicast framework that links each block interval to quorum formation latency. We capture multimodal block time distributions using mixture models, where each component represents a distinct network condition characterized by effective transfer rate of block information. The proposed model is fitted to the bulk of mainnet block time data, while tail decay is analyzed separately to assess asymptotic behavior. Applying this methodology to Hyperliquid and Aptos mainnets, we find that Hyperliquid is well explained by a unimodal distribution, consistent with a relatively homogeneous validator deployment. In contrast, Aptos exhibits persistent multimodal structure and a pronounced shift following a consensus upgrade, reflecting heterogeneous deployments and diverse communication paths. These results demonstrate that mixture modeling of block time provides a practical and informative diagnostic tool for analyzing and monitoring high-performance BFT consensus.

Arthur Chagas, Pedro Bento, Yan Aquino, Arthur Buzelin · 6 authors

Volatility forecasts are commonly evaluated with aggregate accuracy metrics such as RMSE and MAE, but these metrics can hide conditional failures that matter for risk management. This paper proposes a model-agnostic audit framework for evaluating whether volatility forecasts remain reliable across latent market regimes. We learn time-series representations of market-state windows, cluster them into regimes using only training information, assign regimes out of sample, and compare aggregate forecast behavior with regime-conditional bias, tail-underprediction, and underprediction-sensitive economic losses. Applied to daily volatility forecasting across cryptocurrency and ETF assets, the audit shows that models with competitive aggregate accuracy can still exhibit substantial regime-specific bias and severe tail underprediction. The results suggest that volatility forecasting should be evaluated not only by average error, but also by where and how forecasts become unreliable. Our framework shifts forecast evaluation from asking which model is most accurate on average to identifying the market regimes in which apparently accurate forecasts fail conditionally. Reproducibility: https://github.com/arthurchagas1/Latent-Regime-Bias-Auditing-for-Volatility-Forecasting

Authors unavailable

No abstract is available for this record.

Ryan Anthony, Jechenthia Maria Taso, Stephen Yohanes Christopher, Ridhwan Ardiyansyah

This study aims to analyze and compare the performance of three algorithms, namely Support Vector Regression (SVR) with a linear kernel, XGBoost, and LightGBM, in predicting the Price of Ethereum cryptocurrency based on daily historical data. The study uses Ethereum Price data in USD for the last five years obtained from the investing.com website. The variables used are Close, Open, High, and Low Prices. The study uses two data splitting scenarios: 80% training data and 20% testing data, and 70% training data and 30% testing data. This study also uses time step variations to test the effect of time dependency on algorithm performance. The results indicate that the LightGBM algorithm has the best performance compared to the other two algorithms with an average MAE value for High Price of 75.486, SVR has a value of 115.590, and XGBoost has a value of 77.314 in the 80% training data and 20% testing data split. In the 70% training data and 30% testing data split, the LightGBM algorithm still excels with an average MAE value for High Price of 78.228, SVR of 104.356, and XGBoost of 83.573. Other evaluations such as RMSE and R2 also show the superiority of the LightGBM algorithm. For the required computation time, the SVR algorithm outperforms the other two algorithms.

Claudio Boido, Lewin Jones

Active asset managers increasingly include cryptocurrencies in their alternative asset allocations, highlighting their speculative and volatile nature. The aim of this research is to examine trends in the returns and volatility of cryptocurrencies, whilst accounting for the depegging of stablecoins, driven by speculative trading during macroeconomic shocks and technological shifts. We build a sample of market capitalisation, using data from the daily closing prices of Bitcoin (BTC), Ethereum (ETH), Binance (BNB), and Ripple (XRP), two fiat-backed stablecoins (USDT and USDC), and a cryptocurrency-collateralised stablecoin (DAI). As a first step, a Granger-causality framework is applied to examine the influence of stablecoin depegging events on crypto returns during financial market stress. The results are strongly asymmetric: there is little evidence that depegs predict returns; whereas cryptocurrency returns robustly Granger-cause USDC depegging events, an effect that intensifies during periods of market stress. Stablecoin depegs appear to be a downstream symptom of cryptocurrency stress rather than a leading indicator of it. The analysis was extended by modelling volatility, using an EGARCH-X model to study whether depegs also affect crypto during periods of market stress and if larger deviations from the dollar peg are associated with higher cryptocurrency volatility, concentrated in the most liquid stablecoins (USDT and USDC), while the evidence for any change in this association during stress is limited. The findings carry implications for risk monitoring in digital-asset markets, where stablecoin behaviour reflects, rather than anticipates, cryptocurrency market conditions.

Avtandil Gagnidze, Maksim Iavich

Since 2008, when the cryptocurrency was first introduced under the name Satoshi Nakamoto, more and more people are interested in the «new money» – Bitcoin. Bitcoin is the first cryptocurrency and although many other cryptocurrencies were created and will be created in the future, Bitcoin remains the most popular cryptocurrency to this day. Naturally, along with the rapid growth of information technologies and their applications, many new «computerized» currencies will emerge. Because anyone can buy and sell cryptocurrency (e.g. bitcoin) and, thus, cryptocurrency is a subject of trade, hence cryptocurrency and in particular bitcoin is a product. Naturally, questions arise about the determinants of cryptocurrency price changes. In particular: Are the changes in the prices of cryptocurrency (and in particular Bitcoin) related to the development trends of the global economy? Are changes in the prices of cryptocurrency (and in particular Bitcoin) related to indicators of the state of the global economy, such as the well-known indices DJII, Nasdaq, S&P 500 and others. Thus it is interesting to see whether it is possible to predict changes in the prices of cryptocurrencies (and in particular Bitcoin) using different methods of time series.

Nydia REMOLINA LEON, Aurelio GURREA-MARTINEZ, Daniel LIU

This article provides a comprehensive analysis of the treatment of digital assets in insolvency. Given that cryptoassets can be the subject of various transactions—including purchase, sale, custody, and lending—understanding their nature and implications in insolvency is relevant for any firm, not just cryptoexchanges. The article begins by offering a general overview of the world of cryptoassets. It then examines the nature of cryptoassets from accounting, financial, and legal perspectives. While much of the literature on insolvency and cryptoassets has primarily focused on the analysis of whether cryptocurrencies constitute property of the estate, this article explores additional issues, such as the treatment, role and rights of tokenholders in insolvency, the initiation of insolvency proceedings by cryptolenders, and the valuation, recovery, and realization of digital assets in bankruptcy. Such analysis is conducted from a comparative perspective, examining how jurisdictions around the world have addressed some of those issues and how cryptoassets have been used to engineer innovative solutions in restructuring agreements.

Avtandil Gagnidze, Maksim Iavich

With the improvement of data technology advances and the sharp addition of web customers number since the 90s, numerous computerized monetary standards are presented. the most popular among them is Bitcoin. It was decided to investigate the possible relations between the most popular cryptocurrency Bitcoin price dynamics and global Nasdaq index dynamics using Mathematical and Statistical methods. The main question is: Are the Bitcoin prices somehow related with Nasdaq Composite Index? We use both, Quantitative and Qualitative data analysis methods to answer this question: Namely, the Regression model and Non­-Parametric testing. According to Quantitative methods, it was found that there exists a correlation and the regression equation is not bed: it seems that it is possible to explain about 60% of changes in Bitcoin Prices by changes in the Nasdaq Index. According to Qualitative methods, it was found that these two variables are independent. In this case, the Qualitative conclusion is more likely to be right, and the correlation is most likely because of coincidence.

Vcc Business

Paying online often means sharing card details with merchants, advertising platforms, software providers, and payment processors. For freelancers, agencies, online sellers, and small teams, that can create unnecessary exposure: a compromised merchant account, an unexpected renewal, or a card number reused across several services may turn into a difficult cleanup project. A virtual card funded through a USDT top up offers another way to separate online spending from a primary bank account while keeping budgets easier to manage. This approach is not a promise of anonymity, approval, or freedom from verification. A responsible provider may still require identity checks, transaction monitoring, and information about the source of funds. The practical benefit is financial separation and control. Instead of giving every website direct access to a bank-linked card, you can use a dedicated card for approved online purchases, review the conversion terms, and keep records for accounting and compliance. Why use USDT to fund a virtual card USDT is a dollar-pegged digital asset commonly used to move value between supported wallets and platforms. When a card provider accepts USDT, it may convert the deposited amount into the card's spending balance, subject to its network, supported blockchain, confirmation requirements, fees, and compliance procedures. This can be useful for users who already hold USDT and want to pay merchants that accept ordinary card payments rather than cryptocurrency directly. The main operational advantage is separation. A dedicated virtual card can be assigned to advertising, SaaS subscriptions, supplier purchases, or a single project. If the card must be frozen or replaced, the issue may be contained to that spending channel instead of requiring changes across a personal bank account and every recurring payment connected to it. How the funding process usually works A typical flow has three stages: you create or select a card, send USDT to a deposit addre Full article attached as Markdown. Published for vccbusiness.com.

Fernando Frachone Neves, André Luiz Oliveira, Flávia Vancim Frachone MASSA, Tainara Adriani Ribeiro de Jesus · 5 authors

A proliferação da tecnologia blockchain e da mineração de criptomoedas tem gerado interesse de especialistas em sustentabilidade, emergindo um novo campo de estudo, desenvolvendo o conceito de criptomoedas verdes e a sustentabilidade digital. Neste sentido, este estudo realizou uma análise bibliométrica com o objetivo de mapear as tendências, estruturas temáticas e avanços na literatura científica sobre sustentabilidade digital no ecossistema blockchain, com foco em criptomoedas verdes. Para isso, foram analisados 133 artigos científicos extraídos do Web of Science (WOS), utilizando-se o software RStudio. Os resultados revelaram um crescimento acelerado de publicações, com um pico em 2024, indicando um campo de pesquisa em rápida expansão. As contribuições em pesquisa demonstram uma polarização, destacando a China e a Índia como principais polos. Temas dominantes incluem "cryptocurrency", "bitcoin", "blockchain technology", "green bonds", "clean energy" e "renewable energy", enquanto o mapeamento temático identificou "energy consumption", "risk" e "green challenges adoption" como temas motores. Esta revisão bibliométrica confirma o crescente interesse em criptomoedas verdes, impulsionado pela necessidade de mitigar impactos ambientais e alinhar a inovação tecnológica aos Objetivos de Desenvolvimento Sustentável (ODS) da ONU. Conclui-se que o estudo oferece percepções importantes aos formuladores de políticas, investidores e desenvolvedores, visando promover um desenvolvimento digital mais equitativo e alinhado à sustentabilidade.

Ayaan Siddiqui

Business Models and Value Creation via the x402 Protocol in Web3

Rukhsar Zaka, Faiza Irfan, Sidra Rehman, Muhammad Ahsan Hayat

Cryptocurrency markets are highly volatile, nonlinear, and affected by several internal and external market factors, making price forecasting a challenging task. Accurate cryptocurrency price forecasting can support investors, traders, and financial analysts in making informed decisions. This research paper presents a comparative analysis of machine learning and deep learning models for cryptocurrency price forecasting using historical Aave (AAVE) cryptocurrency data. The dataset consists of 275 records and 10 features, including Date, High, Low, Open, Close, Volume, and Marketcap. The Close price is selected as the target variable, while High, Low, Open, Volume, and Marketcap are used as predictor variables. Five models are implemented and compared: Linear Regression, Support Vector Regression, Random Forest Regressor, XGBoost Regressor, and Long Short-Term Memory. The models are evaluated using Mean Absolute Error, Root Mean Square Error, Mean Absolute Percentage Error, R-squared score, and directional accuracy. Experimental results show that the LSTM model achieved the best performance with the lowest RMSE of 2.74, MAE of 1.78, MAPE of 3.91%, and R-squared score of 0.965. The results indicate that deep learning models, especially LSTM, are more suitable for capturing temporal dependencies and nonlinear patterns in cryptocurrency price data.

Ningyu Zhou

This paper examines whether information stress affects trading frictions and liquidity resilience in cryptocurrency markets. Using public information proxies and OHLCV-based friction indicators, the analysis applies local projections to trace the response of trading conditions. The results show that information stress mainly affects trading frictions in the short run. Spread-based friction reacts immediately and recovers quickly, while the Amihud-based proxy adjusts more gradually. The cumulative effect is strongest in the early horizons and weaker over longer horizons. Overall, information stress creates temporary trading pressure rather than persistent deterioration in market resilience.

Marion Bonazzi

This country profile demonstrates how France plays a leading role in the FCT domain, ranking amongst the top beneficiaries of Horizon Europe funding, with approximately 11.4% of the total allocated budget. French stakeholders are highly engaged in cross-sector projects, frequently assuming coordination responsibilities or leading key work packages. A distinctive feature of France’s participation is the role of the Police Nationale and Gendarmerie Nationale, two key actors in many EU-funded security projects. Their involvement ensures a strong alignment between research activities and real-world law enforcement needs, particularly in areas such as Internal Security, Crisis Management, and the Protection of Public Spaces. Furthermore, a broad ecosystem of public research institutions, governmental bodies, and industrial partners contributes to the national effort. France’s research and innovation community is actively involved across a wide range of FCT priorities, including Artificial Intelligence, Cybersecurity, Border Management, and Digital Transformation. Beyond technological development, French actors also play a significant role in shaping regulatory frameworks and promoting the exchange of best practices, particularly in law enforcement and judicial cooperation. Overall, France shows strong participation in Horizon Europe, with representatives in over half of FCT-funded projects, particularly in activities related to the dark web and cryptocurrencies, the trafficking of humans and goods, and strong support for training and exercises. We’re collecting feedback on this report through the EU Survey Platform, if you’d like to share your thoughts please click on the link below. https://ec.europa.eu/eusurvey/runner/enact-report-feedback

Gloria Onyarin

The rapid digitalization of financial services has transformed the global financial ecosystem, enabling faster transactions, enhanced customer experiences, and greater financial inclusion. However, this digital transformation has simultaneously increased the complexity, scale, and sophistication of financial fraud. Traditional rule-based fraud detection systems often struggle to identify evolving fraud patterns, resulting in delayed responses, increased false positives, and substantial financial losses. Artificial Intelligence (AI)-powered real-time fraud monitoring systems have emerged as a transformative solution capable of detecting suspicious activities instantly through advanced data analytics, machine learning, deep learning, natural language processing, and behavioral intelligence. These systems continuously analyze vast volumes of transactional and non-transactional data, enabling financial institutions to identify anomalies, predict fraudulent behavior, and automate risk management processes with unprecedented accuracy and speed. This literature review examines the evolution, applications, technological foundations, benefits, challenges, and future directions of AI-powered real-time fraud monitoring systems in modern financial services. The review highlights how AI enhances fraud detection capabilities across banking, payment systems, insurance, digital wallets, cryptocurrencies, and investment platforms while discussing critical concerns related to privacy, algorithmic bias, explainability, cybersecurity, and regulatory compliance. The findings demonstrate that AI-driven fraud monitoring represents a fundamental component of modern financial security infrastructure and will continue to shape the future of fraud prevention in increasingly digital financial environments.

Maja CZYŻEWSKA

This paper empirically compares four architectures for financial time-series forecasting: LSTM, CNN, the original Regularized Self Attention Regression (RSAR) model, and a multiobjective optimized RSAR variant, denoted MO-RSAR, obtained using the Non dominated Sorting Genetic Algorithm II (NSGA-II). The models are evaluated on six datasets covering Forex, equity index and cryptocurrency markets, for short and long horizons. All models share a common preprocessing pipeline and evaluation framework and are assessed using standard error metrics, with emphasis on Mean Absolute Percentage Error (MAPE). MORSAR yields the lowest average prediction error across all datasets and provides significant gains for longer, more volatile horizons, while simpler architectures remain competitive for short-term forecasts. The key methodological contribution is the first empirical integration of the RSAR architecture with NSGA-IIbased multi-objective hyperparameter optimization for financial time-series forecasting. The proposed framework treats RSAR configuration as a bi-objective search over accuracy and generalization (via the train-validation gap), and evaluates the resulting model under a unified protocol across heterogeneous markets and horizons.