The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.
problem Sequential decision making in high-frequency markets under evolving uncertainty.
method Analyzes two dimensions of robustness: uncertainty tolerance and action robustness, using simulations and empirical evidence.
result Action robustness has a larger impact on profitability than uncertainty tolerance, and excessive robustness can reduce profitability in illiquid markets.
The paper analyzes RL in high-frequency market making with theoretical and practical implications.
problem Applying RL to high-frequency market making with theoretical rigor.
method Theoretical analysis bridging RL and financial economics, focusing on sampling frequency effects.
result An interesting tradeoff between error and complexity in RL algorithms as sampling frequency decreases.
DRL agents perform poorly at high decision frequencies, but a new algorithm improves performance.
problem DRL agents struggle at high decision frequencies, leading to poor performance.
method Proved that DRL agents' action-conditioned return distributions collapse to their policy's return distribution as decision frequency increases. Defined superiority as a probabilistic generalization of advantage for high-frequency value-based RL.
result Proper modeling of superiority distribution improves performance of controllers at high decision frequencies.
A method for fast, accurate cross-temporal forecasts using machine learning.
problem Inconsistent forecasts across different levels of platform data.
method Non-linear hierarchical forecast reconciliation using machine learning.
result Automated direct production of reconciled forecasts for high-frequency decision making.
MacroHFT uses memory and context-aware reinforcement learning to improve HFT performance.
problem Overfitting and biased decisions in HFT due to rapid market changes.
method Memory Augmented Context-aware Reinforcement Learning (MacroHFT) that trains multiple sub-agents and a hyper-agent.
result MacroHFT achieves state-of-the-art performance on minute-level trading tasks.
Survey of AI in finance covering models, strategies, and knowledge systems.
problem Challenges in applying AI to financial markets, especially in high-frequency trading.
method Systematic analysis of financial AI across predictive models, decision frameworks, and knowledge augmentation systems.
result Critical trade-offs and gaps between theoretical advances and practical implementation in financial AI.
Hybrid model combines VAR and neural network for OFI prediction.
problem Accurate prediction of Order Flow Imbalance (OFI) in high frequency trading.
method Combines Vector Auto Regression (VAR) and a simple feedforward neural network (FNN).
result Hybrid model achieves superior predictive accuracy compared to standalone models.
A new high-frequency market making strategy using Deep Hawkes process.
problem Optimizing high-frequency trading in volatile markets.
method Developed a Deep Hawkes process to model order arrivals and their effects on the limit order book.
result The new strategy outperforms traditional methods in market making.
Proposes a deep RL approach for high-frequency market making using tick data and periodic signals.
problem Challenges in high-frequency market making due to tick-level data complexity and high trading volume.
method Integrates tick-level data with periodic signals using deep reinforcement learning.
result The proposed framework outperforms existing methods in profitability and risk management.
Trains a neural network to predict high-frequency trading outcomes.
problem Predicting the fill probability function for high-frequency trading.
method High-quality high-frequency data and neural network training with a weighted loss function.
result Strong state dependence properties of the fill probability function.
This paper uses Gaussian processes to forecast short-term stock price volatility.
problem Inaccurate short-term volatility forecasts for high-frequency trades.
method Combines numerical and probabilistic models, specifically Gaussian Processes (GPs), to correct and forecast stock price data.
result Effective short-term volatility forecasts for high-frequency trades using Gaussian Processes.
This paper explores how RL enhances HFT strategies in volatile markets.
problem Adapting to changing market dynamics in HFT.
method Deep Q-Learning applied to statistical arbitrage strategies.
result RL improves adaptability and profitability in HFT.
In the present work we introduce a novel multi-agent model with the aim to reproduce the dynamics of a double auction market at microscopic time scale through a faithful simulation of the matching mechanics in the limit order book. The agents follow a noise decision making process where their actions are related to a s…
AI traders learn to exploit meta-orders from slower traders, increasing their profits.
problem Adverse selection of medium-frequency traders by high-frequency AI agents.
method Reinforcement learning in a Hawkes LOB model, with impulse control and PPO.
result AI agents can learn to capitalize on meta-orders, increasing their profits.
EarnHFT tackles HFT challenges with hierarchical RL, significantly outperforming existing methods.
problem Challenges in applying RL to HFT due to long trajectories and market volatility.
method Three-stage hierarchical RL framework: Q-teacher, diverse RL agents, and minute-level router.
result Significantly outperforms 6 state-of-the-art baselines in profitability.
Hybrid model uses GNNs and pathfinding to optimize portfolio rebalancing costs.
problem Optimizing transaction costs in dynamic portfolio rebalancing.
method Combines GNNs for cost prediction and Dijkstra's algorithm for pathfinding.
result Significantly reduces transaction costs in financial asset graphs.
Neural nets analyze crypto markets for multi-timeframe trading.
problem High-frequency trading in cryptocurrency markets.
method Multi-timeframe trend analysis and high-frequency direction prediction networks.
result Positive risk-adjusted returns through machine learning.
Detects corruption in agentic models during execution.
problem Inconsistent context, retrieval errors, or adversarial inputs corrupt intermediate steps of reasoning chains.
method Analyzes token graphs induced by attention and computes spectral statistics to emit accept/reject signals.
result A single threshold on the high frequency energy ratio optimally detects context inconsistency in agentic models.
RL agents optimize order execution in a realistic market simulation.
problem Optimal order execution challenges in a complex market.
method Multi-agent RL in a historical order book simulation.
result RL agents converge to TWAP strategies in some scenarios.
JaxMARL-HFT accelerates MARL for HFT with 240x speedup.
problem Heavy computational cost in MARL for HFT.
method GPU-accelerated JAX framework for multi-agent RL.
result Agents learn to outperform benchmarks in HFT.
Improved language models learn complex distributions using Fourier series.
problem Capturing continuous structure in discrete token distributions.
method Introducing a Fourier head layer to model continuous structures.
result Significant improvements in performance across various tasks.
A novel framework extracts essential factors from order flow data for high-frequency trading.
problem Challenges in extracting and utilizing order flow data due to its large volume and limitations of traditional techniques.
method Proposes a Context Encoder and Factor Extractor for unsupervised learning of important signals from order flow data.
result Extracts superior factors from order flow data, improving stock trend prediction and order execution tasks.
Based on iterative optimization and activation function in deep learning, we proposed a new analytical framework of high-frequency trading information, that reduced structural loss in the assembly of Volume-synchronized probability of Informed Trading (VPIN), Generalized Autoregressive Conditional Heteroscedasticity …
DeepVol uses high-frequency data to forecast volatility, outperforming traditional methods.
problem Improving volatility forecasting using high-frequency data.
method Dilated Causal Convolutions applied to high-frequency financial time-series.
result DeepVol outperforms traditional methods in forecasting day-ahead volatility.
This paper introduces a high frequency trade execution model to evaluate the economic impact of supervised machine learners. Extending the concept of a confusion matrix, we present a 'trade information matrix' to attribute the expected profit and loss of the high frequency strategy under execution constraints, such as …
DSI improves tail-risk estimation in generative models by averaging checkpoints.
problem Generative models' instability in rare adverse scenarios.
method Diachronic Sample Integration (DSI) ensembles generated samples across checkpoints.
result DSI reduces tail-estimation error compared to single-checkpoint baselines.
Study evaluates three ML models for high-frequency trading.
problem Improving accuracy and reliability of high-frequency trading strategies.
method Compared three models: cross-entropy loss + quasi-Newton, FCNN, and vector machine.
result Combination of cross-entropy loss and quasi-Newton outperformed other models.
This review explores causal decision-making to improve decision quality.
problem Effective decision-making requires understanding causal relationships.
method Causal structure learning, causal effect learning, and causal policy learning.
result Challenges in causal decision-making are identified and recent advances are discussed.
We analyze a tractable model of a limit order book on short time scales, where the dynamics are driven by stochastic fluctuations between supply and demand. We establish the existence of a limiting distribution for the highest bid, and for the lowest ask, where the limiting distributions are confined between two thresh…
Study on HFTs' interactions with a large trader using mean field game theory.
problem Interactions between high-frequency traders and a large trader executing assets at discrete times.
method Modeling HFTs' behavior using a jump process and solving the equilibrium through mean field game approach.
result Inventory-averse HFTs lower LT's costs when market impact is large.
This paper develops a framework for efficient decision-making under time pressure.
problem Efficient decision-making under time pressure and subjective tradeoffs.
method Unified framework for evidence-based decision-making under time pressure.
result Ability to model and understand decision-making behavior under time constraints.
Study minimax-optimal rates for offline decision-making with function approximation.
problem Statistical complexity of offline decision-making with function approximation.
method Near minimax-optimal rates for stochastic contextual bandits and Markov decision processes, using pseudo-dimension and behavior policy.
result Established performance limits and new characterization of behavior policy.
Framework for robust decision making in changing environments with privacy constraints.
problem Interactive decision making in changing environments with constraints.
method Hybrid Decision Making with Structured Observations (hybrid DMSO) framework, local differentially private decision making, query-based learning, robust and smooth decision making.
result Strong connections and bounds derived for DEC, SQ dimension, local minimax complexity, learnability, and joint differential privacy.
MDS selects assets by combining daily returns and intraday risk curves, improving portfolio performance.
problem High estimation error in large-scale asset selection.
method Metric Dependence Screening (MDS) incorporating high frequency information as object valued data.
result MDS improves portfolio performance over benchmarks by preserving intraday risk dynamics.
Continuous high frequency water quality monitoring is becoming a critical task to support water management. Despite the advancements in sensor technologies, certain variables cannot be easily and/or economically monitored in-situ and in real time. In these cases, surrogate measures can be used to make estimations by me…
ALPE improves mid-price forecasting in HFT with real-time data.
problem Real-time mid-price forecasting in high-frequency trading.
method Adaptive Learning Policy Engine (ALPE) using RL and adaptive epsilon decay.
result ALPE outperforms other models in mid-price forecasting.
Study adversarial attacks on automated trading systems.
problem Robustness of deep learning models in algorithmic trading.
method New attacks with size constraints to evaluate model robustness.
result Realistic adversarial attacks can fool automated trading systems.
Study uses multi-kernel Hawkes models to analyze high-frequency price dynamics.
problem Understanding responsive speeds of market participants in high-frequency trading.
method Multi-kernel Hawkes models with conditional Hessian analysis for optimization.
result Existence of multi-kernels (UHF, VHF, HF) in high-frequency price dynamics.
Paper tackles risk-sensitive decision-making under uncertainty.
problem Risk-sensitive decision-making problem under uncertainty.
method Formulated as a stochastic control problem, delineated necessary optimality conditions.
result Illustrative examples from optimal betting and inventory management support the theory.
New active learning strategy improves decision-making accuracy.
problem Maximizing decision-making accuracy in sequential data acquisition.
method Introduces a novel active learning criterion that maximizes expected information gain on the posterior decision distribution.
result Improved performance in decision-making accuracy compared to existing alternatives.
We propose a framework to study optimal trading policies in a one-tick pro-rata limit order book, as typically arises in short-term interest rate futures contracts. The high-frequency trader has the choice to trade via market orders or limit orders, which are represented respectively by impulse controls and regular con…
The paper tackles individualized decision-making under unmeasured confounding, providing a novel minimax solution and a paradox.
problem Unmeasured confounding in causal inference leads to biased estimates and affects individualized decision-making.
method The authors establish a formal link between individualized decision-making under partial identification and classical decision theory, providing a minimax solution and a paradox.
result A novel minimax solution for individualized decision-making/policy assignment is provided, and an interesting paradox is drawn.
Financial portfolio optimization is a widely studied problem in mathematics, statistics, financial and computational literature. It adheres to determining an optimal combination of weights associated with financial assets held in a portfolio. In practice, it faces challenges by virtue of varying math. formulations, par…
The Chain-of-Decision approach improves forecasting of financial professionals' trading decisions.
problem Challenges in forecasting professionals' behaviors, especially in trading decisions.
method Integrates an opinion-generator-in-the-loop to provide subjective analysis based on news items.
result Promising improvements in the proposed tasks' performance.
A new framework designs experiments for better decision-making.
problem Suboptimal experimental designs for downstream decision-making.
method Amortized decision-aware Bayesian Experimental Design (BED) with Transformer Neural Decision Process (TNDP).
result TNDP effectively designs experiments and facilitates accurate decision-making.
Decision making based on behavioral and neural observations of living systems has been extensively studied in brain science, psychology, and other disciplines. Decision-making mechanisms have also been experimentally implemented in physical processes, such as single photons and chaotic lasers. The findings of these exp…
We model human decision-making behaviors in a risk-taking task using inverse reinforcement learning (IRL) for the purposes of understanding real human decision making under risk. To the best of our knowledge, this is the first work applying IRL to reveal the implicit reward function in human risk-taking decision making…
An online decision-making algorithm using stochastic gradient descent for big data.
problem Efficiently updating decision rules in online decision making with big data.
method Stochastic gradient descent for online updates, asymptotic normality of estimators.
result Asymptotic normality of parameter and value estimators, enabling statistical inference.