The fluctuation characteristics of financial time series have always been one of the research hotspots in the academic community. Generally speaking, financial return series have the characteristics of volatility clustering, fat tails, conditional heteroskedasticity, asymmetric shocks, etc. The above phenomena can be explained from the perspective of dynamic conditional variance by GARCH models and their extensions. This paper first introduces the basic ideas of ARCH and GARCH models, with a focus on the issue of volatility clustering of financial returns. Then, it reviews the relevant research from three aspects: model evolution, application scenarios, and practical value. It also analyzes the role of GARCH-type models in capturing volatility persistence, asymmetric impact, and risk transmission through applications in cryptocurrencies, energy assets, and high-frequency financial data. The study shows that GARCH-type models capture the volatility clustering feature of financial returns well, but there is still room to improve the modeling of extreme risk, the handling of high-dimensional assets, and model interpretability.
Crypto currency is one of most interesting financial innovation of 21st century. Crypto currency trading not only involve financial literacy while trading but also there are psychological factors affecting the decision of traders. Keeping in view the psychological factors and investorsâ decision, this research study is designed to investigate the complex interplay between psychological triggers and market dynamics in the cryptocurrency sector in Pakistan, specifically examining how these elements coalesce to drive investor behavior and market volatility. While traditional financial models often attribute asset fluctuations to technological or fundamental shifts, this study posits that cryptocurrency markets are fundamentally driven by human perception and emotional reactivity. Utilizing a quantitative methodological approach, data was collected from a sample of 175 experienced traders to analyze the impact of emotional states, market sentiment, and behavioral discipline on trading outcomes. The empirical results, derived through multiple linear regression analysis, reveal that the model possesses a high level of explanatory power, accounting for 56% of the variance in emotional trading behavior (R2=0.56R2=0.56). Market sentiment emerged as the primary determinant of impulsive trading (β=0.48β=0.48), demonstrating that external social cues often exert a stronger influence on decision-making than internal emotional states. Among specific psychological variables, Fear, Uncertainty, and Doubt (FUD) were identified as the most significant predictors of rash choices (β=0.34β=0.34), while the Fear of Missing Out (FOMO) also demonstrated a substantial, though secondary, effect (β=0.21β=0.21). Conversely, the study found that trading experience and the application of systematic strategies serve as vital moderating factors that decrease emotional reactivity and enhance behavioral stability (β=â0.19β=â0.19). The findings contribute to the fields of behavioral finance and digital economics by illustrating that the volatility inherent in digital assets is a systemic byproduct of individual psychological biases aggregated through digital narratives. The research concludes that achieving a sustainable financial ecosystem requires moving beyond purely technical regulations. Instead, it advocates for the implementation of behaviorally-informed safeguards, such as algorithmic "cooling-off" periods and sentiment-aware trading tools, to mitigate the risks associated with reactive investing. Ultimately, this work provides a blueprint for a more resilient digital financial future by prioritizing human factors in market governance.
Initial Coin Offerings (ICOs) have emerged as an innovative mechanism for raising capital, particularly for blockchain-based projects. However, the lack of regulatory oversight and the prevalence of low-quality information raise important questions about what truly drives ICO success. While existing literature focuses predominantly on technical and signalling variables, the role of investor decision-making remains theoretically underdeveloped and empirically underexplored. This paper addresses this gap by pursuing two objectives. First, we identify the drivers of ICO success using a probit model applied to an original sample of 535 ICOs conducted between January 2016 and May 2021. Second, we investigate investor decision-making patterns using a novel dataset of 200 active crypto-forum participants over the same period. Our results have three main findings, though with modest statistical strength than initially estimated. (I) Marketing channels are the most consistent predictor of ICO success across the sample period, clearing conventional significance thresholds only in the pooled sample (z = 1.90, p<0.10), with each additional channel raising the probability of soft-cap achievement by approximately 1.0 percentage point. (II) Team presentation and video presentation show no meaningful influence on success in any period. (III) Whitepaper availability is not statistically significant even in pooled sample, reinforcing rather than qualifying its irrelevance as a predictor; the number of accepted cryptocurrency price speculation rather than project fundamentals, consistent with mood and sentiment dominating information-based decision making in ICO markets, though this finding should be read alongside the data limitations discussed in 3.B. These findings contribute to the behavioural finance literature by providing an operational definition of âinvestor moodâ and demonstrating its empirical relevance in crypto markets. We conclude that understanding investor mood is not a secondary question but a necessary complement to technical analysis of ICO success.
Decentralised finance (DeFi) is a relatively new trend in finance that uses blockchain, smart contracts, and distributed ledger technology to offer financial services in a decentralised manner. Although scholars have made many theoretical advances in decentralised finance in recent years, knowledge of its theoretical structure and future research areas remains limited. This is why this study provides a bibliometric analysis of 1002 articles on DeFi published in Scopus between 2012 and 2026. The analysis uses performance analysis and a science mapping approach based on citation analysis, co-authorship, bibliographic coupling and keyword co-occurrence analysis. The results reveal a remarkably high annual growth rate of 39.34% and DeFiâs dynamism and interdisciplinary nature. The three main countries involved in DeFi research are the USA, China, and the UK. Management Science, Energy Economics and Technological Forecasting and Social Change became the main scientific journals for disseminating knowledge about DeFi. Analysis of thematic changes showed a transition of scientific interests from blockchain and cryptocurrencies to new topics, like artificial intelligence, sustainability, governance, and financial inclusion. Overall, the current study provides a better understanding of the intellectual, conceptual, and social basis of DeFi and highlights possible research areas in the use of artificial intelligence in DeFi, decentralised governance, and sustainable digital financial system development.
This informative document explores the evolving digital asset landscape, covering cryptocurrency, NFTs, blockchain technology, Web3, and emerging market trends. It provides readers with practical insights into digital ownership, market developments, and the importance of research when evaluating opportunities in the growing blockchain economy. Collective Shift
Technological innovations are often perceived as something alien, terrifying, and monstrous. Blockchain technology that creates shared âblocksâ of information, which are interconnected and verified by the network comes as no exception. Two main features of blockchain (1) the absence of a gatekeeper organisation controlling the data, and (2) the fact that the information is rather hard to corrupt and hack, makes the technology very attractive and versatile. It is also what makes it appear frightening, especially for the traditionally centralised and hierarchical disciplines like law. As there is no one to control the data and the access to it, blockchains open a whole world of new possibilities with cryptocurrencies being one of the most popular examples.Approaching blockchain technologies in the context of J. J. Cohenâs monster theory demonstrates that they can be perceived as modern monsters. Our inability to understand the technology and the way it works makes this particular monster both fearful and desired (thesis 6), and law reacts to the fears that circulate in the society. Thus, blockchain technologies are often banned by law in a similar way as in medieval narratives dragons were banished by saints and heroes. Building on Cohenâs thesis 7, which argues that monsters show how we (mis)interpret our surroundings, this article will employ the historical perspective upon the fear of the monstrous to create a better understanding of the legal policies surrounding blockchains. By comparing current legal decisions concerning blockchain technology with the strategies of dealing with monsters, offered by medieval chronicles and collections of wonders (including William of Malmesbury and William of Newburgh), we will analyse the modern way of controlling monsters â or controlling the fear of them.
This perspective examines whether nuclear fusion can provide a scalable, low-carbon power source for rapidly growing AI-driven data center demand. As large language models, cloud computing, and cryptocurrency mining accelerate electricity consumption growth, data centers are projected to account for a substantially larger share of U.S. and global electricity use in the coming decades, creating significant pressure on grid reliability and decarbonization goals. We evaluate the technical and economic alignment between data center load profiles and nuclear power, particularly fusion, through a comparative analysis of capacity factors, levelized cost of electricity, grid interconnection constraints, and deployment pathways. Unlike intermittent renewables, nuclear fission and fusion offer high-capacity-factor, firm baseload generation suited to AI training and inference workloads that require continuous, reliable power. Preliminary techno-economic analysis suggests that several Nth-of-a-kind fusion concepts, particularly magnetic confinement systems, may become cost-competitive with firmed renewable systems and advanced fission for hyperscale data center applications. Co-location of fusion plants with data centers further reduces transmission bottlenecks, improves resilience, and aligns with emerging hyperscaler procurement strategies. We also assess recent regulatory developments and argue that fusion's favorable safety profile and reduced waste burden improve its long-term social and political viability relative to fission. We conclude that fusion represents a strategically important pathway for sustainably powering next-generation computing infrastructure and should be prioritized in both policy and industrial deployment planning.
The Triadic Stress Index (TSI) takes a network index whose four factors were first observed in soil microbiome co-occurrence networks and applies it, without alteration, to the correlation network of financial assets. We test it on five markets spanning 2006-2026 (equities including banking crises and the AI sector, cryptocurrencies, commodities, foreign exchange and sovereign debt), against three independent definitions of a crisis episode, at a fixed alarm budget, out of sample, with block-bootstrap intervals and a Holm correction across the family of tests. The benchmarks are the Absorption Ratio, the industry standard used by MSCI and central banks; the effective rank and the Vendi score, the sharpest spectral measures available; Ollivier-Ricci curvature; and the global and local balance indices of signed correlation networks. Three comparisons favour the index. It carries a per-node decomposition, diag(A^3), naming which asset is carrying the concentration with no parameter to select, and scores 0.97-0.99 against 0.33-0.84 for the only published per-node alternative, whereas spectral attribution must first choose how many components to read and collapses under a standard but wrong choice. Its alarms are the cleanest of anything tested, 4.0% of them with no matching episode against 14.7% for the effective rank and roughly 59% for the Absorption Ratio. And it beats the Absorption Ratio on detection by 0.273 in F1 out of sample, p<0.0005. The remaining comparisons are ties. Against the effective rank and the Vendi score the index ties in every scheme and both samples, and the margin over the Absorption Ratio narrows under the strictest labelling. On real matrices the far simpler node degree reproduces the attribution. A lead-lag analysis puts the peak cross-correlation at zero lag: this is a coincident state index, not a forecast.
This study investigates whether the macroscopic statistical maturity of cryptocurrencies implies dynamical equivalence with traditional equity markets. We analyze high-frequency data (2020--2025) using the Complexity--Entropy Causality Plane (CECP) and directed horizontal visibility graphs (directed HVG) to uncover complex temporal patterns and time-directed structures in the return series. While conventional stylized facts show striking convergence across all assets, structural diagnostics reveal a compelling paradox: cryptocurrencies appear more locally random than the equity benchmark during ordinary periods, yet exhibit significantly stronger directional time-irreversibility around high-visibility return events. The absolute-return results show that large cryptocurrency fluctuations tend to begin abruptly and remain elevated afterward. Separate analyses of positive returns and negative-return magnitudes show that this pattern is shared across cryptocurrencies on the upside but varies across assets on the downside. We conclude that statistical maturity is only skin-deep; the underlying dynamical processes of mature cryptocurrencies remain fundamentally distinct from traditional benchmarks.
Ira Nath, Sanjukta Chatterjee, Rangan Nath, Rumpa Paul ¡ 5 authors
CryptC provides users with secure wallet services to protect their digital cryptocurrency assets as a modern cryptocurrency solution. Multiple platforms can adopt CryptC through the React Native interface while users can enjoy easy access using authentication from Firebase and Firestore for data and security features. Ganache with ethers.js enables the wallet to perform safe blockchain transactions while operating on a local Ethereum blockchain through its Ganache access. Secure compliance requirements are achieved by the platform through its transaction logging system and scalable functionality and biometric asset security measures, and balance update capabilities. The platform features an interface that combines professional and beginner user capabilities through an interactive dashboard, together with horizontal list presentation and user-focused design execution. The DeFi (Decentralized finance) ecosystem tool CryptC provides real-time operation capabilities that outperforms conventional wallet features like PIN base verification, Real-time Ethereum (ETH) transaction, minimalistic mobile-friendly UI etc. Our work provides comprehensive information about CryptC, along with its unique design specification through android App and security protocols, while validating the platform for payments at multiple operational levels.
This paper examines how Bitcoin returns interact with macroeconomic and financial driversâspecifically inflation, industrial production, money supply, stock market returns, the wholesale price index, and financial conditionsâusing monthly data from April 2015 to March 2025. Methodologically, we apply Augmented Dickey-Fuller (ADF) tests, ordinary least squares (OLS) regression, and vector autoregression (VAR) modelling. Because not all variables are stationary at levels, the VAR model is estimated with differencing. The OLS results indicate that traditional macroeconomic factors do not effectively explain Bitcoin returns. However, the VAR analysis reveals that inflation significantly Granger-causes Bitcoin returns, whereas financial conditions and equity markets show negligible predictive power. Impulse response functions confirm that macroeconomic shocks hit Bitcoin only in the short term, and variance decomposition shows that over 84% of Bitcoinâs volatility is driven by its own innovations. We conclude that Bitcoin remains a largely decoupled, self-driven asset with minimal integration into traditional macroeconomic fundamentals, despite a modest predictive link to inflation. JEL classification numbers: G12, E31, E44. Keywords: Cryptocurrency, macroeconomic, VAR model, ADF test.
Cryptocurrency exchange-traded products (ETPs) listed on European exchanges provide a regulated environment for studying intraday market anomalies. We study four Bitcoin and Ethereum ETPs traded on Xetra and Nasdaq Stockholm over the period January 2024 - December 2025 using one-minute bars. As a benchmark, we adopt an extreme value theory approach in which anomalous bars are defined as returns falling below a threshold estimated by fitting a generalised Pareto distribution to left-tail exceedances. We then propose three new binary anomaly indicators. The first, a cross-venue divergence anomaly, identifies venue-specific price divergence between the two exchanges. The second is a no-recovery anomaly that identifies extreme price drops followed by little or no recovery over the next ten active bars. The third is a momentum-reversal anomaly that identifies extreme price drops following positive short-term momentum. Although each anomaly type represents fewer than 1% of one-minute bars, statistical analysis using Mann-Whitney U tests shows that anomaly observations exhibit significantly higher effective spreads, higher values of liquidity-related ratios, and more pronounced order-flow imbalances than non-anomalous bars. Furthermore, employing an out-of-sample prediction methodology with four classifiers - random forest, logistic regression, extreme gradient boosting, and light gradient boosting machine - shows that all four anomaly types are predictable one bar ahead, with AUC-ROC values of up to 0.82. Permutation importance indicates that short-term volatility and drawdown measures are generally more useful for prediction than microstructure variables.
Operations research has long contributed to addressing energy and environmental challenges through mathematical modeling and decision-support methods. In particular, numerous studies have examined investment planning, capacity expansion, and policy design for renewable energy systems under uncertainty. As efforts to achieve carbon neutrality intensify worldwide, the expansion of renewable energy has become a critical policy and investment priority. However, the inherent variability of renewable power generation and the substantial upfront investment costs continue to hinder investment decisions and limit the adoption of renewable energy. To address the economic challenges associated with renewable energy penetration, recent studies have explored the use of cryptocurrency mining as a means of monetizing surplus renewable electricity. This study contributes to this emerging research stream by developing a real options model that captures the interaction between renewable energy investment and cryptocurrency mining under uncertainty. The numerical results show that cryptocurrency mining increases the value of renewable energy investment and accelerates investment by lowering the investment threshold. Moreover, the equilibrium determination of mining capacity reduces the renewable energy investment threshold by approximately 40.5% compared with the benchmark in which mining capacity is specified exogenously.
Velian Prapatoni, Rizky Parlika, Firza Prima Aditiawan
Cryptocurrency markets are characterized by high volatility, rapid price fluctuations, and substantial uncertainty, creating challenges for investment risk interpretation. This study develops a descriptive risk-interpretation framework, rather than a price-prediction or decision-optimization model, by integrating multi-scale volatility analysis with technical indicators. A quantitative descriptive design was applied to approximately one year of historical hourly price data for Bitcoin and Ethereum, covering open, high, low, close, volume, and percentage change attributes. The data were chronologically sorted, numerically cleaned and normalized, transformed into log returns, and analyzed through rolling standard deviation. Volatility was estimated across three explicitly defined horizons: short-term 7-period, medium-term 30-period, and long-term 90-period rolling windows. Moving Average (MA), Relative Strength Index (RSI), and Average True Range (ATR) were then incorporated to contextualize trend direction, momentum, and fluctuation intensity. The results show that volatility is strongly horizon-dependent: short-term movements responded more sharply to market shocks, whereas longer horizons produced smoother risk patterns. Across the analyzed Bitcoin and Ethereum hourly series, the reported 42.3% short-term and 21.7% medium-term increases were calculated as relative differences against long-term rolling volatility during identified high-uncertainty intervals, not as predictive accuracy measures. These findings indicate that combining rolling volatility with MA, RSI, and ATR can improve the transparency of descriptive cryptocurrency risk assessment. The framework may support preliminary interpretation for novice or risk-averse investors, although it does not empirically test investor comprehension or subsequent decision quality.
Mohammad Quthbul Widad, Rizky Parlika, Firza Prima Aditiawan
Although Bitcoin is acknowledged as the largest cryptocurrency by market capitalization and trading volume in the world's financial market, investors face a great deal of risk and uncertainty due to its exceptionally high volatility and non-linear price changes. To provide a data-driven foundation for risk reduction and forecasting support, accurate modeling techniques are crucial. This work attempts to provide a thorough comparative analysis mapping the precise accuracyâefficiency trade-off between Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models under a standardized Grid Search hyperparameter optimization pipeline using a recent Bitcoin closing-price dataset spanning from January 1, 2020, to January 1, 2026. The research methodology follows a structured data science pipeline, beginning with data acquisition from Yahoo Finance, followed by preprocessing using Min-Max Scaling fitted strictly on the training partition to eliminate data leakage. Model development involves an experimental approach where both LSTM and GRU neural controllers are tuned to extract optimal structural weights. The predictive precision of these models is rigorously evaluated using three standard metrics: MAE, RMSE, and MAPE, while processing throughput is measured via hardware execution times. The research findings indicate that the optimized LSTM model achieved superior one-step-ahead predictive precision with a MAPE of 2.32%, whereas the GRU model recorded a higher error rate of 3.94%. However, the GRU model demonstrated a significant advantage in computational efficiency, completing the training process 8.45 times faster than LSTM. In conclusion, while LSTM is recommended as a forecasting support tool for high-precision financial analysis, GRU remains a viable, parameter-efficient alternative for real-time monitoring on resource-constrained systems before real-world financial deployment.
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 instrumentâBitcoin, IDX30 stocks, and Goldâduring 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 KruskalâWallis 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 KruskalâWallis 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 â 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.
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 standardâs 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 .
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 classesâForeign Exchange (EUR/USD), Commodities (XAU/USD and USOIL), and Cryptocurrencies (BTC/USD)âDEM-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.
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
Imagine the hunt to predict Bitcoin&s;s wildly swinging price as a high-stakes competition among four clever computer programs, because investors really need to know where it&s;s headed to make smart plans. Our study pitted these programsâthe classic ARIMA, the modern Facebook Prophet, the powerful XGBoost, and the deep-learning LSTM networkâagainst each other to see which could best guess future Bitcoin prices. Using two main report cards, the MAE and RMSE scores, we found that Prophet and ARIMA were neck-and-neck, but the XGBoost model completely missed the mark, proving highly inaccurate with very high error scores. However, the true champion turned out to be the LSTM neural network, which blew the others out of the water by delivering the lowest error scores on both test and training data, essentially making it the most reliable tool for anyone looking to build a winning strategy in the tricky world of crypto trading.
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.
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 capitalizationâBitcoin, Ethereum, Tether, Binance Coin, XRP, USD Coin, Solana, TRON, Dogecoin, and Hype liquidâusing 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 JarqueâBera test of normality, the WaldâWolfowitz 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 cryptocurrenciesâBitcoin, Ethereum, Tether, Binance Coin, XRP, USD Coin, and Dogecoinâdo 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.
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 (2022â2025) 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 3Ă 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.