Study integrates deep learning with financial data for improved trading strategies.
problem Enhancing predictive performance in algorithmic trading and portfolio optimization.
method Developed embedding techniques to treat limit order book snapshots as image-based input channels.
result Achieved state-of-the-art performance in high-frequency trading algorithms.
The paper examines the reliability of limit order book representations in the face of data perturbation.
problem The reliability of limit order book representations under data perturbation.
method Experimental analysis of existing representations and guidelines for future research.
result Existing representations of limit order book data are vulnerable to data perturbation.
Model predicts limit order book dynamics based on market participant interactions.
problem Understanding and predicting the dynamics of the limit order book in financial markets.
method Agent-based model with informed, noise, and market maker traders; deduces limit order book from interactions.
result Link between price dynamics, trade proportions, volume, spread, and equilibrium state.
Machine learning predicts short-term price movements from LOB features.
problem Understanding and predicting short-term price movements from LOB dynamics.
method Machine learning approach to analyze LOB features.
result Significantly superior prediction results compared to baseline.
Deep learning model improves financial return forecasting using LOBs.
problem Forecasting financial returns using Limit Order Books.
method Developed a deep learning architecture for simultaneous quantile regression of buy and sell positions.
result The model provides improved robustness and excellent performance in predicting financial returns.
The model analyzes order flows in financial markets using Cox-type intensities.
problem Analyzing order dynamics in limit order books for market insights.
method Cox-type model for relative intensities, parameter estimation by quasi likelihood maximization, model selection with information criteria.
result The model provides excellent agreement with empirical data and identifies important factors in order book dynamics.
Simulates financial market orders using anomalous diffusion models.
problem Anomalous diffusion in financial market order dynamics.
method Discrete Time Random Walk with Sibuya waiting times, non-uniform sampling, and cubic spline interpolation.
result Demonstrates price impact for different forcing functions and model parameters.
Paper uses ML to predict stock price movements from order book data.
problem Forecasting stock price movements in financial markets.
method Combines handcrafted and ML features for three classifiers, evaluated on two setups.
result Machine Learning shows promise for this task, suggesting future research.
Models predict order book recovery from aggressive trading follows a simple t^1/3 scaling.
problem Understanding order book dynamics in financial markets.
method Developed macroscopic models and solved numerically and asymptotically.
result Order book recovery follows a t^1/3 scaling law.
Model uses statistical physics principles to predict financial market volatility and returns.
problem Predicting price volatility and expected returns in financial markets.
method Inspired by statistical physics, the study introduces a physical model using Level 3 order book data to measure kinetic energy and momentum.
result The model outperforms traditional and machine learning approaches in forecasting volatility and expected returns.
Paper examines GCHP for mid-price prediction in financial data.
problem Predicting mid-price in financial data with stochastic models.
method General Compound Hawkes Process (GCHP) for mid-price prediction.
result GCHP models show potential for predicting mid-price direction and volatility.
In an incomplete financial market, the axiomatic of Time Consistent Pricing Procedure (TCPP), recently introduced, is used to assign to any financial asset a dynamic limit order book, taking into account both the dynamics of basic assets and the limit order books for options. Kreps-Yan fundamental theorem is extended t…
Financial markets can be described on several time scales. We use data from the limit order book of the London Stock Exchange (LSE) to compare how the fluctuation dominated microstructure crosses over to a more systematic global behavior.
Multivariate Hawkes processes analyze order dynamics in financial markets.
problem Complex interactions between order timing and size in financial markets.
method Multivariate Hawkes processes with nonparametric estimation.
result Simple volume-time independence models are inadequate for financial data.
In this paper we present a novel approach to the determination of fat tails in financial data by studying the information contained in the limit order book. In an order-driven market buyers and sellers may submit limit orders, which are executed when the price touches a pre-specified lower, respectively higher, limit-p…
RL agent learns to place limit orders for trading signals in financial markets.
problem Training an RL agent to execute trading signals in limit order book markets.
method Deep Duelling Double Q-learning with APEX architecture, using synthetic alpha signals.
result RL agent outperforms heuristic trading strategies in inventory management and order placing.
Proposes a stochastic model for limit order book dynamics.
problem Captures the dynamics of limit order books in financial markets.
method Develops a stochastic partial differential equation (SPDE) model with multiplicative noise.
result Shows efficient estimation and computation methods for the model.
RNNs predict price-flips in limit order books, reducing adverse selection.
problem Predicting price-flips in limit order books to reduce adverse selection.
method Recurrent Neural Networks (RNNs) applied to high-frequency trading data.
result RNNs capture non-linear relationships and outperform other classifiers.
The paper develops a diffusion model for limit order book dynamics.
problem Modeling the complex dynamics of limit order books in financial markets.
method Derives a diffusion approximation for discrete-time limit order book models with non-linear dynamics.
result The discrete dynamics converge to a diffusion limit under suitable assumptions.
Models interactions among market participants in a financial asset's order book.
problem Understanding dynamic interactions among market participants in a financial asset's order book.
method Derives variational partial differential equations for MM and HFT strategies, and explains almost optimal control.
result Illustrates interactions between market participants through simulations of an order book.
LOB-Bench benchmarks generative AI for financial data, outperforming traditional models.
problem Lack of consensus on evaluating generative AI models for financial data.
method Python-based benchmark with LOB statistics and market impact metrics.
result Generative autoregressive models outperform traditional models in LOB data.
New MGCPP model for order flow in financial markets.
problem Modeling order flow dynamics in financial markets.
method Developed MGCPP, proved LLN and FCLTs, applied to real data.
result Validated MGCPP model with real trading data.
New model reveals latent liquidity in financial markets.
problem Understanding the connection between latent and observable order books.
method Suggests a simple mechanism for revealing latent liquidity and quantifies it from real data.
result Existence of a market instability threshold leading to liquidity crises.
The paper models liquidity in financial markets using a string model of order books.
problem Tackles the arbitrage and pricing issues in financial markets.
method Develops a dynamic market model with order books and proves no arbitrage under certain conditions.
result Generically, there is no arbitrage in the model when noise is a stochastic string.
Study forecasts cryptocurrency returns using LOB data and Hawkes model.
problem Predicting cryptocurrency returns due to their chaotic nature.
method Hawkes model applied to LOB data with COE model.
result Outperforms benchmarks in cryptocurrency return sign forecasting.
Optimal trading strategies in fluctuating financial markets are analyzed using complex mathematical models.
problem Optimal execution of trades in markets with fluctuating liquidity and order book depth.
method Continuous-time limit order book model with càdlàg semimartingale strategies, quadratic BSDEs.
result Characterization of minimal execution costs and existence of optimal strategies.
Framework detects covert financial market manipulation using LOB representations.
problem Detecting covert financial market manipulation (spoofing) from complex anomaly patterns in multilevel prices.
method Cascaded contrastive representation learning of LOB data.
result Transformer-based architectures achieve state-of-the-art results in detection performance.
JAX-LOB simulates thousands of LOBs for RL training.
problem Efficient simulation of large LOBs for RL training.
method GPU-accelerated JAX implementation of LOB simulator.
result JAX-LOB processes thousands of LOBs in parallel with reduced processing time.
Paper connects micro to macro models of limit order books using SPDEs.
problem Modeling high-frequency trading dynamics in limit order books.
method Microscopic to mesoscopic to macroscopic limit analysis, SPDEs.
result Macroscopic limit described by reflected SPDEs.
It has been suggested that marked point processes might be good candidates for the modelling of financial high-frequency data. A special class of point processes, Hawkes processes, has been the subject of various investigations in the financial community. In this paper, we propose to enhance a basic zero-intelligence o…
Paper provides a benchmark dataset for mid-price forecasting in limit order book data.
problem Forecasting mid-price in high-frequency financial markets.
method Extracted and normalized time series data from NASDAQ Nordic stocks.
result Dataset of ~4,000,000 time series samples for 5 stocks.
Generative diffusion models improve financial LOB simulation and forecasting.
problem High noise and complexity in financial LOB data makes deep generative models ineffective.
method Convert LOB data to images, apply diffusion models with inpainting for long-term sequence generation.
result Our method achieves state-of-the-art performance on LOB-Bench, improving coherence over local details.
A new model for financial limit order books using stochastic partial differential equations.
problem Modeling financial limit order books with phase transitions.
method Stochastic partial differential equations (SPDEs) and maximal Lp-regularity. result Existence, uniqueness, and regularity of local solutions observed.
HLOB predicts mid-price changes in L.O.Bs using deep learning.
problem Forecasting mid-price changes in Limit Order Books.
method HLOB uses a deep learning model with an Information Filtering Network and Homological Convolutional Neural Networks.
result HLOB outperforms state-of-the-art models in real-world datasets.
We formalize how markets aggregate via arbitrage and quantify liquidity loss.
problem How financial markets aggregate and the loss of liquidity.
method Characterize markets via utility functions, use thermodynamics analogy, derive limit order book representation, compute aggregation loss.
result Arbitrage-mediated aggregation leads to market-dynamical entropy quantifying liquidity loss.
The study classifies and imitates trading agents in financial markets.
problem Classifying and imitating trading agents in continuous double auctions.
method Developed an agent-based model for trading, applied opponent modeling for classification, and used behavioral cloning for imitation.
result Techniques for classification and imitation were experimentally compared and evaluated.
A Hawkes process with state-dependent factor models order flows in limit order books.
problem Modeling order flows in limit order books for better market prediction.
method A Hawkes process with a state-dependent factor for conditional intensity estimation.
result State-dependent formulations improve the fit of LOB models to financial data.
Generative model predicts financial market order flow with high accuracy.
problem Creating realistic order flow models for financial markets.
method Token-level autoregressive generative model using deep state space layers.
result Model generates high-quality order flow data with low perplexity.
Study finds strong long-range correlations in financial markets, especially over longer time scales.
problem Understanding long-range correlations in limit order book markets.
method Ultra-high frequency order book data from NASDAQ Nordic, detrended fluctuation analysis (DFA).
result Strong evidence of long-range correlation in inter-event durations, becoming stronger over longer time scales.
Hybrid model simulates market dynamics using neural stochastic background traders.
problem Lack of realistic LOB simulations that combine historical data and dynamic interactions.
method Neural stochastic background trader trained on historical LOB data, embedded in multi-agent simulation.
result Hybrid model recreates stylised market facts and financial herding behaviors.
A quasi-centralized limit order book (QCLOB) is a limit order book (LOB) in which financial institutions can only access the trading opportunities offered by counterparties with whom they possess sufficient bilateral credit. We perform an empirical analysis of a recent, high-quality data set from a large electronic tra…
Optimal trade execution in a fluctuating market with stochastic liquidity.
problem Minimizing costs in a market with unpredictable liquidity.
method Developed a recursion to find the least costly trade execution strategy.
result Explicit recursion characterizes the least costly trade execution.
Deep RL controller outperforms market making benchmarks in a Hawkes process model.
problem Optimal market making in financial markets.
method Deep reinforcement learning on a Hawkes process-based simulator.
result Deep RL controller outperforms benchmarks in various risk-reward metrics.
High Frequency Trading (HFT) represents an ever growing proportion of all financial transactions as most markets have now switched to electronic order book systems. The main goal of the paper is to propose continuous time equations which generalize the self-financing relationships of frictionless markets to electronic …
Through the analysis of a dataset of ultra high frequency order book updates, we introduce a model which accommodates the empirical properties of the full order book together with the stylized facts of lower frequency financial data. To do so, we split the time interval of interest into periods in which a well chosen r…
Proposes a neural LOB model for market-making.
problem Capturing dynamic LOB events in financial markets.
method Neural Hawkes process for modeling LOB events.
result Model captures real market price fluctuations.
A multivariate Hawkes process with sum-of-three-exponentials kernel fits limit order book data well.
problem Capturing clustering behavior in financial systems using Hawkes processes.
method Fitted multivariate Hawkes process with sum-of-three-exponentials kernel to limit order book data, tested for goodness-of-fit and stationarity.
result Sum-of-three-exponentials kernel yields the best fit to coupled point processes.
The distribution of returns in financial time series exhibits heavy tails. In empirical studies, it has been found that gaps between the orders in the order book lead to large price shifts and thereby to these heavy tails. We set up an agent based model to study this issue and, in particular, how the gaps in the order …