Deep learning for limit order books
From MaRDI portal
Abstract: This paper develops a new neural network architecture for modeling spatial distributions (i.e., distributions on R^d) which is computationally efficient and specifically designed to take advantage of the spatial structure of limit order books. The new architecture yields a low-dimensional model of price movements deep into the limit order book, allowing more effective use of information from deep in the limit order book (i.e., many levels beyond the best bid and best ask). This "spatial neural network" models the joint distribution of the state of the limit order book at a future time conditional on the current state of the limit order book. The spatial neural network outperforms other models such as the naive empirical model, logistic regression (with nonlinear features), and a standard neural network architecture. Both neural networks strongly outperform the logistic regression model. Due to its more effective use of information deep in the limit order book, the spatial neural network especially outperforms the standard neural network in the tail of the distribution, which is important for risk management applications. The models are trained and tested on nearly 500 stocks. Techniques from deep learning such as dropout are employed to improve performance. Due to the significant computational challenges associated with the large amount of data, models are trained with a cluster of 50 GPUs.
Recommendations
- A deep learning approach to estimating fill probabilities in a limit order book
- Deep learning for market by order data
- A generative model of a limit order book using recurrent neural networks
- Online Learning in Limit Order Book Trade Execution
- Deep reinforcement learning for the optimal placement of cryptocurrency limit orders
- Reinforcement learning equilibrium in limit order markets
- Encoding of high-frequency order information and prediction of short-term stock price by deep learning
Cites work
- A continuous and efficient fundamental price on the discrete order book grid
- A fully consistent, minimal model for nonlinear market impact
- A mathematical approach to order book modeling
- A stochastic model for order book dynamics
- Adaptive execution: exploration and learning of price impact
- An empirical comparison of classification algorithms for mortgage default prediction: evidence from a distressed mortgage market
- Classification-based financial markets prediction using deep neural networks
- DGM: a deep learning algorithm for solving partial differential equations
- Enhancing trading strategies with order book signals
- Fluctuations and response in financial markets: the subtle nature of `random' price changes
- Forecasting prices from level-I quotes in the presence of hidden liquidity
- Gaussian process-based algorithmic trading strategy identification
- High-frequency trading in a limit order book
- scientific article; zbMATH DE number 6378127 (Why is no real title available?)
- HYDRODYNAMIC LIMIT OF ORDER-BOOK DYNAMICS
- Linear models for the impact of order flow on prices. I. History dependent impact models
- Linear models for the impact of order flow on prices. II: The mixture transition distribution model
- Modelling high-frequency limit order book dynamics with support vector machines
- Multilayer feedforward networks are universal approximators
- Optimal execution with non-linear transient market impact
- OR forum: The cost of latency in high-frequency trading
- Price dynamics in a Markovian limit order market
- Probability density estimation using artificial neural networks
- Queueing dynamics and state space collapse in fragmented limit order book markets
- Reducing transaction costs with low-latency trading algorithms
- Sequential design for optimal stopping problems
- Statistical emulators for pricing and hedging longevity risk products
- Stochastic gradient descent in continuous time
- The Long Memory of the Efficient Market
- The price impact of order book events: market orders, limit orders and cancellations
- The self-financing equation in limit order book markets
- Universal features of price formation in financial markets: perspectives from deep learning
- Using neural network rule extraction and decision tables for credit-risk evaluation
- What really causes large price changes?
- Why is equity order flow so persistent?
Cited in
(32)- Forecasting financial time series with Boltzmann entropy through neural networks
- Quantum blind signature scheme for supply chain financial
- Order scoring, bandit learning and order cancellations
- Deep reinforcement learning for the optimal placement of cryptocurrency limit orders
- Optimal market-making strategies under synchronised order arrivals with deep neural networks
- Deep-Learning Solution to Portfolio Selection with Serially Dependent Returns
- Online Learning in Limit Order Book Trade Execution
- A deep learning approach to estimating fill probabilities in a limit order book
- A reinforcement learning approach to optimal execution
- On detecting spoofing strategies in high-frequency trading
- Double deep Q-learning for optimal execution
- Forecasting jump arrivals in stock prices: new attention-based network architecture using limit order book data
- Deep prediction of investor interest: a supervised clustering approach
- Deep learning for market by order data
- Universal features of price formation in financial markets: perspectives from deep learning
- Encoding of high-frequency order information and prediction of short-term stock price by deep learning
- Learning multi-market microstructure from order book data
- Optimal Execution: A Review
- Data-driven hedging of stock index options via deep learning
- Cross-impact of order flow imbalance in equity markets
- Deep attentive survival analysis in limit order books: estimating fill probabilities with convolutional-transformers
- A two-step framework for arbitrage-free prediction of the implied volatility surface
- Optimal liquidation through a limit order book: a neural network and simulation approach
- A generative model of a limit order book using recurrent neural networks
- Deep order flow imbalance: Extracting alpha at multiple horizons from the limit order book
- Fin-GAN: forecasting and classifying financial time series via generative adversarial networks
- Weight bound constraints in mean-variance models: a robust control theory foundation via machine learning
- Asymptotic behavior of the maximum likelihood estimator for general Markov switching models
- Deep limit order book forecasting: a microstructural guide
- Attention-based reading, highlighting, and forecasting of the limit order book
- Generative-discriminative machine learning models for high-frequency financial regime classification
- Bimodal dynamics of the artificial limit order book stock exchange with autonomous traders
This page was built for publication: Deep learning for limit order books
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5234311)
