Cryptocurrency price dynamics are driven largely by microstructural supply demand imbalances in the limit order book (LOB), yet the highly noisy nature of LOB data complicates the signal extraction process. Prior research has demonstrated that deep-learning architectures can yield promising predictive performance on pre-processed equity and futures LOB data, but they often treat model complexity as an unqualified virtue. In this paper, we aim to examine whether adding extra hidden layers or parameters to "blackbox ish" neural networks genuinely enhances short term price forecasting, or if gains are primarily attributable to data preprocessing and feature engineering. We benchmark a spectrum of models from interpretable baselines, logistic regression, XGBoost to deep architectures (DeepLOB, Conv1D+LSTM) on BTC/USDT LOB snapshots sampled at 100 ms to multi second intervals using publicly available Bybit data. We introduce two data filtering pipelines (Kalman, Savitzky Golay) and evaluate both binary (up/down) and ternary (up/flat/down) labeling schemes. Our analysis compares models on out of sample accuracy, latency, and robustness to noise. Results reveal that, with data preprocessing and hyperparameter tuning, simpler models can match and even exceed the performance of more complex networks, offering faster inference and greater interpretability.
The paper explores the use of Deep Reinforcement Learning (DRL) in stock market trading, focusing on two algorithms: Double Deep Q-Network (DDQN) and Proximal Policy Optimization (PPO) and compares them with Buy and Hold benchmark. It evaluates these algorithms across three currency pairs, the S&P 500 index and Bitcoin, on the daily data in the period of 2019-2023. The results demonstrate DRL's effectiveness in trading and its ability to manage risk by strategically avoiding trades in unfavorable conditions, providing a substantial edge over classical approaches, based on supervised learning in terms of risk-adjusted returns.
This research systematically develops and evaluates various hybrid modeling approaches by combining traditional econometric models (ARIMA and ARFIMA models) with machine learning and deep learning techniques (SVM, XGBoost, and LSTM models) to forecast financial time series. The empirical analysis is based on two distinct financial assets: the S&P 500 index and Bitcoin. By incorporating over two decades of daily data for the S&P 500 and almost ten years of Bitcoin data, the study provides a comprehensive evaluation of forecasting methodologies across different market conditions and periods of financial distress. Models' training and hyperparameter tuning procedure is performed using a novel three-fold dynamic cross-validation method. The applicability of applied models is evaluated using both forecast error metrics and trading performance indicators. The obtained findings indicate that the proper construction process of hybrid models plays a crucial role in developing profitable trading strategies, outperforming their individual components and the benchmark Buy&Hold strategy. The most effective hybrid model architecture was achieved by combining the econometric ARIMA model with either SVM or LSTM, under the assumption of a non-additive relationship between the linear and nonlinear components.
Autonomous Market Makers (AMMs) rely on arbitrage to facilitate passive price updates. Liquidity fragmentation poses a complex challenge across different blockchain networks. This paper proposes FluxLayer, a solution to mitigate fragmented liquidity and capture the maximum extractable value (MEV) in a cross-chain environment. FluxLayer is a three-layer framework that integrates a settlement layer, an intent layer, and an under-collateralised leverage lending vault mechanism. Our evaluation demonstrates that FluxLayer can effectively enhance cross-chain MEV by capturing more arbitrage opportunities, reducing costs, and improving overall liquidity.
Although modern blockchains almost universally produce blocks at fixed intervals, existing models still lack an analytical formula for the loss-versus-rebalancing (LVR) incurred by Automated Market Makers (AMMs) liquidity providers in this setting. Leveraging tools from random walk theory, we derive the following closed-form approximation for the per block per unit of liquidity expected LVR under constant block time: \[ \overline{\mathrm{ARB}}= \frac{\,σ_b^{2}} {\,2+\sqrt{2π}\,γ/(|ζ(1/2)|\,σ_b)\,}+O\!\bigl(e^{-\mathrm{const}\tfracγ{σ_b}}\bigr)\;\approx\; \frac{σ_b^{2}}{\,2 + 1.7164\,γ/σ_b}, \] where $σ_b$ is the intra-block asset volatility, $γ$ the AMM spread and $ζ$ the Riemann Zeta function. Our large Monte Carlo simulations show that this formula is in fact quasi-exact across practical parameter ranges. Extending our analysis to arbitrary block-time distributions as well, we demonstrate both that--under every admissible inter-block law--the probability that a block carries an arbitrage trade converges to a universal limit, and that only constant block spacing attains the asymptotically minimal LVR. This shows that constant block intervals provide the best possible protection against arbitrage for liquidity providers.
This paper investigates real-time detection of spoofing activity in limit order books, focusing on cryptocurrency centralized exchanges. We first introduce novel order flow variables based on multi-scale Hawkes processes that account both for the size and placement distance from current best prices of new limit orders. Using a Level-3 data set, we train a neural network model to predict the conditional probability distribution of mid price movements based on these features. Our empirical analysis highlights the critical role of the posting distance of limit orders in the price formation process, showing that spoofing detection models that do not take the posting distance into account are inadequate to describe the data. Next, we propose a spoofing detection framework based on the probabilistic market manipulation gain of a spoofing agent and use the previously trained neural network to compute the expected gain. Running this algorithm on all submitted limit orders in the period 2024-12-04 to 2024-12-07, we find that 31% of large orders could spoof the market. Because of its simple neuronal architecture, our model can be run in real time. This work contributes to enhancing market integrity by providing a robust tool for monitoring and mitigating spoofing in both cryptocurrency exchanges and traditional financial markets.
Building on our prior threshold-based analysis of six months of Poloniex trading data, we have extended both the temporal span and granularity of our study by incorporating minute-level OHLCV records for 1021 tokens around each confirmed pump-and-dump event. First, we algorithmically identify the accumulation phase, marking the initial and final insider volume spikes, and observe that 70% of pre-event volume transacts within one hour of the pump announcement. Second, we compute conservative lower bounds on insider profits under both a single-point liquidation at 70% of peak and a tranche-based strategy (selling 20% at 50%, 30% at 60%, and 50% at 80% of peak), yielding median returns above 100% and upper-quartile returns exceeding 2000%. Third, by unfolding the full pump structure and integrating social-media verification (e.g., Telegram announcements), we confirm numerous additional events that eluded our initial model. We also categorize schemes into "pre-accumulation" versus "on-the-spot" archetypes-insights that sharpen detection algorithms, inform risk assessments, and underpin actionable strategies for real-time market-integrity enforcement.
From viral jokes to a billion-dollar phenomenon, meme coins have become one of the most popular segments in cryptocurrency markets. Unlike utility-focused crypto assets like Bitcoin, meme coins derive value primarily from community sentiment, making them vulnerable to manipulation. This study presents an unprecedented cross-chain analysis of the meme coin ecosystem, examining 34,988 tokens across Ethereum, BNB Smart Chain, Solana, and Base. We characterize their tokenomics and track their growth in a three-month longitudinal analysis. We discover that among high-return tokens (>100%), an alarming 82.8% show evidence of artificial growth strategies designed to create a misleading appearance of market interest. These include wash trading and a new form of manipulation we define as Liquidity Pool-Based Price Inflation (LPI), where small strategic purchases trigger dramatic price increases. We find that profit extraction schemes, such as pump and dumps and rug pulls, typically follow initial manipulations like wash trading or LPI, indicating how early manipulations create the foundation for later exploitation. We quantify the economic impact of these schemes, identifying over 17,000 victimized addresses with realized losses exceeding $9.3 million. These findings reveal that combined manipulations are widespread among high-performing meme coins, suggesting that their dramatic gains are often driven by coordinated efforts rather than natural market dynamics.
Masterminds are entities organizing, coordinating, and orchestrating cryptocurrency pump-and-dump schemes, a form of trade-based manipulation undermining market integrity and causing financial losses for unwitting investors. Previous research detects pump-and-dump activities in the market, predicts the target cryptocurrency, and examines investors and \ac{osn} entities. However, these solutions do not address the root cause of the problem. There is a critical gap in identifying and tracing the masterminds involved in these schemes. In this research, we develop a detection system \textsc{Perseus}, which collects real-time data from the \acs{osn} and cryptocurrency markets. \textsc{Perseus} then constructs temporal attributed graphs that preserve the direction of information diffusion and the structure of the community while leveraging \ac{gnn} to identify the masterminds behind pump-and-dump activities. Our design of \textsc{Perseus} leads to higher F1 scores and precision than the \ac{sota} fraud detection method, achieving fast training and inferring speeds. Deployed in the real world from February 16 to October 9 2024, \textsc{Perseus} successfully detects $438$ masterminds who are efficient in the pump-and-dump information diffusion networks. \textsc{Perseus} provides regulators with an explanation of the risks of masterminds and oversight capabilities to mitigate the pump-and-dump schemes of cryptocurrency.
We construct liquidity-adjusted return and volatility using purposely designed liquidity metrics (liquidity jump and liquidity diffusion) that incorporate additional liquidity information. Based on these measures, we introduce a liquidity-adjusted ARMA-GARCH framework to address the limitations of traditional ARMA-GARCH models, which are not effectively in modeling illiquid assets with high liquidity variability, such as cryptocurrencies. We demonstrate that the liquidity-adjusted model improves model fit for cryptocurrencies, with greater volatility sensitivity to past shocks and reduced volatility persistence of erratic past volatility. Our model is validated by the empirical evidence that the liquidity-adjusted mean-variance (LAMV) portfolios outperform the traditional mean-variance (TMV) portfolios.
Decentralized exchanges (DEXs) face persistent challenges in liquidity retention and user engagement due to inefficiencies in conventional automated market maker (AMM) designs. This work proposes a dual-mechanism framework to address these limitations: a ``Better Market Maker (BMM)'', which is a liquidity-optimized AMM based on a power-law invariant ($X^nY = K$, $n = 4$), and a dynamic rebate system (DRS) for redistributing transaction fees. The segment-specific BMM reduces impermanent loss by 36\% compared to traditional constant-product ($XY = K$) models, while retaining 3.98x more liquidity during price volatility. The DRS allocates fees ($γV$, $γ\in \{0.003, 0.005, 0.01\}$) with a rebate ratio $ρ\in [0.3, 0.4]$ to incentivize trader participation and maintain continuous capital injection. Simulations under high-volatility conditions demonstrate impermanent loss reductions of 36.0\% and 40\% higher user engagement compared to static fee models. By segmenting markets into high-, mid-, and low-volatility regimes, the framework achieves liquidity depth comparable to centralized exchanges (CEXs) while maintaining decentralized governance and retaining value within the cryptocurrency ecosystem.
Jakob Albers, Mihai Cucuringu, Sam Howison, Alexander Y. Shestopaloff
Using data from a live trading experiment on the Binance Bitcoin perpetual, we examine the effects of (i) basic order book mechanics and (ii) the persistence of price changes from immediate to short timescales, revealing the interplay between returns, queue sizes, and orders' queue positions. We document a fundamental trade-off: a negative correlation between maker fill likelihood and post-fill returns. This dictates that viable maker strategies often require a contrarian approach, counter-trading the prevailing order book imbalance. These dynamics render commonly-cited strategies highly unprofitable, leading us to model `Reversals': situations where a contrarian maker strategy at the touch proves effective.
Price Trend Prediction (PTP) based on Limit Order Book (LOB) data is a fundamental challenge in financial markets. Despite advances in deep learning, existing models fail to generalize across different market conditions and assets. Surprisingly, by adapting a simple MLP-based architecture to LOB, we show that we surpass SoTA performance; thus, challenging the necessity of complex architectures. Unlike past work that shows robustness issues, we propose TLOB, a transformer-based model that uses a dual attention mechanism to capture spatial and temporal dependencies in LOB data. This allows it to adaptively focus on the market microstructure, making it particularly effective for longer-horizon predictions and volatile market conditions. We also introduce a new labeling method that improves on previous ones, removing the horizon bias. We evaluate TLOB's effectiveness across four horizons, using the established FI-2010 benchmark, a NASDAQ and a Bitcoin dataset. TLOB outperforms SoTA methods in every dataset and horizon. Additionally, we empirically show how stock price predictability has declined over time, -6.68 in F1-score, highlighting the growing market efficiency. Predictability must be considered in relation to transaction costs, so we experimented with defining trends using an average spread, reflecting the primary transaction cost. The resulting performance deterioration underscores the complexity of translating trend classification into profitable trading strategies. We argue that our work provides new insights into the evolving landscape of stock price trend prediction and sets a strong foundation for future advancements in financial AI. We release the code at https://github.com/LeonardoBerti00/TLOB.
This work focuses on a self-exciting point process defined by a Hawkes-like intensity and a switching mechanism based on a hidden Markov chain. Previous works in such a setting assume constant intensities between consecutive events. We extend the model to general Hawkes excitation kernels that are piecewise constant between events. We develop an expectation-maximization algorithm for the statistical inference of the Hawkes intensities parameters as well as the state transition probabilities. The numerical convergence of the estimators is extensively tested on simulated data. Using high-frequency cryptocurrency data on a top centralized exchange, we apply the model to the detection of anomalous bursts of trades. We benchmark the goodness-of-fit of the model with the Markov-modulated Poisson process and demonstrate the relevance of the model in detecting suspicious activities.
Cryptocurrency portfolio management requires the fusion of heterogeneous multi-modal signals, including structured price and on-chain time series, unstructured news text, and technical indicators, under high-volatility and real-time constraints. While deep learning approaches show predictive capability, their opacity limits practical adoption, and single large language model (LLM) agents struggle to process the breadth of modality-specific inputs needed for robust decision-making. We propose a multi-agent system (MAS) framework in which three modality-specialised agents, a Crypto Agent for market dynamics, a News Agent for weekly news sentiment, and a Trading Agent for signal fusion and portfolio execution, decompose the task across three communication architectures: hierarchical, collaborative, and debate. We evaluate four capability configurations: zero-shot, chain-of-thought (CoT), retrieval-augmented generation (RAG), and skill-augmented. In a 52-week backtest over calendar year 2025 across the top 15 L1 blockchain native cryptocurrencies by market capitalisation as of January 2025, the best configuration, Hierarchical (Skill), achieves a cumulative return of 133.52% and a Sharpe ratio of 1.502, outperforming single-agent variants, passive benchmarks, and deep learning baselines. An ablation study identifies the Crypto Agent as the most critical component, with its removal reducing cumulative return by 42.57 percentage points. A cross-model comparison further shows that MAS outperforms the single-agent baseline under GPT-4o, GPT-5, and Claude Sonnet 4.5, suggesting that the benefit of multi-agent coordination is model-agnostic. Unlike black-box deep learning models, every portfolio decision is traceable to explicit agent reasoning, offering an interpretable and effective approach to multi-modal cryptocurrency portfolio management.
The article investigates the usage of Informer architecture for building automated trading strategies for high frequency Bitcoin data. Three strategies using Informer model with different loss functions: Root Mean Squared Error (RMSE), Generalized Mean Absolute Directional Loss (GMADL) and Quantile loss, are proposed and evaluated against the Buy and Hold benchmark and two benchmark strategies based on technical indicators. The evaluation is conducted using data of various frequencies: 5 minute, 15 minute, and 30 minute intervals, over the 6 different periods. Although the Informer-based model with Quantile loss did not outperform the benchmark, two other models achieved better results. The performance of the model using RMSE loss worsens when used with higher frequency data while the model that uses novel GMADL loss function is benefiting from higher frequency data and when trained on 5 minute interval it beat all the other strategies on most of the testing periods. The primary contribution of this study is the application and assessment of the RMSE, GMADL, and Quantile loss functions with the Informer model to forecast future returns, subsequently using these forecasts to develop automated trading strategies. The research provides evidence that employing an Informer model trained with the GMADL loss function can result in superior trading outcomes compared to the buy-and-hold approach.
Decentralized finance (DeFi) lacks centralized oversight, often resulting in heightened volatility. In contrast, centralized finance (CeFi) offers a more stable environment with institutional safeguards. Institutional backing can play a stabilizing role in a hybrid structure (HyFi), enhancing transparency, governance, and market discipline. This study investigates whether HyFi-like cryptocurrencies, those backed by institutions, exhibit lower price risk than fully decentralized counterparts. Using daily data for 18 major cryptocurrencies from January 2020 to November 2024, we estimate panel EGLS models with fixed, random, and dynamic specifications. Results show that HyFi-like assets consistently experience lower price risk, with this effect intensifying during periods of elevated market volatility. The negative interaction between HyFi status and market-wide volatility confirms their stabilizing role. Conversely, greater decentralization is strongly associated with increased volatility, particularly during periods of market stress. Robustness checks using quantile regressions and pre-/post-Terra Luna subsamples reinforce these findings, with stronger effects observed in high-volatility quantiles and post-crisis conditions. These results highlight the importance of institutional architecture in enhancing the resilience of digital asset markets.
Two MEV builders now produce nearly 80\% of Ethereum blocks. Block builders have the ability to reorder transactions on the blockchain in a way that can be harmful to participants. We estimate they would pay in the aggregate nearly \$14 million per month to ensure that they remained in the first quartile of the block. Sandwich attacks, in which a transaction is front-run, are frequent, averaging more than one per block. Gas fees on these transactions pay for nearly 15\% of the MEV payments to the validator. These attacks have especially large marginal effects and skew the distribution. Reforms such as gas fee priority or private transaction pools might be helpful.
This paper develops a rigorous mathematical framework for analyzing Concentrated Liquidity Market Makers (CLMMs) in Decentralized Finance (DeFi) within a continuous-time setting. We model the evolution of liquidity profiles as measure-valued processes and characterize their dynamics under continuous trading. Our analysis encompasses two critical aspects of CLMMs: the mechanics of concentrated liquidity provision and the strategic behavior of arbitrageurs. We examine three distinct arbitrage models -- myopic, finite-horizon, and infinite-horizon with discounted and ergodic controls -- and derive closed-form solutions for optimal arbitrage strategies under each scenario. Importantly, we demonstrate that the presence of trading fees fundamentally constrains the admissible price processes, as the inclusion of fees precludes the existence of diffusion terms in the price process to avoid infinite fee generation. This finding has significant implications for CLMM design and market efficiency.
Marcin Wątorek, Marcin Królczyk, Jarosław Kwapień, Tomasz Stanisz · 5 authors
Multifractality is a concept that helps compactly grasping the most essential features of the financial dynamics. In its fully developed form, this concept applies to essentially all mature financial markets and even to more liquid cryptocurrencies traded on the centralized exchanges. A new element that adds complexity to cryptocurrency markets is the possibility of decentralized trading. Based on the extracted tick-by-tick transaction data from the Universal Router contract of the Uniswap decentralized exchange, from June 6, 2023, to June 30, 2024, the present study using Multifractal Detrended Fluctuation Analysis (MFDFA) shows that even though liquidity on these new exchanges is still much lower compared to centralized exchanges convincing traces of multifractality are already emerging on this new trading as well. The resulting multifractal spectra are however strongly left-side asymmetric which indicates that this multifractality comes primarily from large fluctuations and small ones are more of the uncorrelated noise type. What is particularly interesting here is the fact that multifractality is more developed for time series representing transaction volumes than rates of return. On the level of these larger events a trace of multifractal cross-correlations between the two characteristics is also observed.
Wash trading, the practice of simultaneously placing buy and sell orders for the same asset to inflate trading volume, has been prevalent in cryptocurrency markets. This paper investigates whether wash traders in Bitcoin act deliberately to exploit market conditions and identifies the characteristics of such manipulative behavior. Using a unique dataset of 18 million transactions from Mt. Gox, once the largest Bitcoin exchange, I find that wash trading intensifies when legitimate trading volume is low and diminishes when it is high, indicating strategic timing to maximize impact in less liquid markets. The activity also exhibits spillover effects across platforms and decreases when trading volumes in other asset classes like stocks or gold rise, suggesting sensitivity to broader market dynamics. Additionally, wash traders exploit periods of heightened media attention and online rumors to amplify their influence, causing rapid but short-lived spikes in legitimate trading volume. Using an exogenous demand shock associated with illicit online marketplaces, I find that wash trading responds to contemporaneous events affecting Bitcoin demand. These results advance the understanding of manipulative practices in digital currency markets and have significant implications for regulators aiming to detect and prevent wash trading.
This paper investigates the enhancement of financial time series forecasting with the use of neural networks through supervised autoencoders (SAE), to improve investment strategy performance. Using the Sharpe and Information Ratios, it specifically examines the impact of noise augmentation and triple barrier labeling on risk-adjusted returns. The study focuses on Bitcoin, Litecoin, and Ethereum as the traded assets from January 1, 2016, to April 30, 2022. Findings indicate that supervised autoencoders, with balanced noise augmentation and bottleneck size, significantly boost strategy effectiveness. However, excessive noise and large bottleneck sizes can impair performance.
With the increasing maturity and expansion of the cryptocurrency market, understanding and predicting its price fluctuations has become an important issue in the field of financial engineering. This article introduces an innovative Genetic Algorithm-generated Alpha Sentiment (GAS) blending ensemble model specifically designed to predict Bitcoin market trends. The model integrates advanced ensemble learning methods, feature selection algorithms, and in-depth sentiment analysis to effectively capture the complexity and variability of daily Bitcoin trading data. The GAS framework combines 34 Alpha factors with 8 news economic sentiment factors to provide deep insights into Bitcoin price fluctuations by accurately analyzing market sentiment and technical indicators. The core of this study is using a stacked model (including LightGBM, XGBoost, and Random Forest Classifier) for trend prediction which demonstrates excellent performance in traditional buy-and-hold strategies. In addition, this article also explores the effectiveness of using genetic algorithms to automate alpha factor construction as well as enhancing predictive models through sentiment analysis. Experimental results show that the GAS model performs competitively in daily Bitcoin trend prediction especially when analyzing highly volatile financial assets with rich data.
Evgenii Onishchuk, Maksim Dubovitskii, Eduard Horch
This empirical study presents the Decentralized Exchanges Comparison Service (DECS), a novel tool developed by 1inch Analytics to assess exchange efficiency in decentralized finance. The DECS utilizes swap transaction monitoring and simulation techniques to provide unbiased comparisons of swap rates across various DEXes and aggregators. Analysis of almost 1.2 million transactions across multiple blockchain networks demonstrates that both 1inch Classic and 1inch Fusion consistently outperform competitors. These findings not only validate 1inch's superior rates but also provide valuable insights for continuous protocol optimization and underscore the critical role of data-driven decision-making in advancing DeFi infrastructure.