Machine learning architectures for price formation models
From MaRDI portal
Abstract: Here, we study machine learning (ML) architectures to solve a mean-field games (MFGs) system arising in price formation models. We formulate a training process that relies on a min-max characterization of the optimal control and price variables. Our main theoretical contribution is the development of a posteriori estimates as a tool to evaluate the convergence of the training process. We illustrate our results with numerical experiments for linear dynamics and both quadratic and non-quadratic models.
Recommendations
- Universal features of price formation in financial markets: perspectives from deep learning
- Autoencoder asset pricing models
- Predictive market making via machine learning
- Machine learning for quantitative finance: fast derivative pricing, hedging and fitting
- scientific article; zbMATH DE number 1304915
- Estimating permanent price impact via machine learning
- A machine learning approach to portfolio pricing and risk management for high‐dimensional problems
- Machine learning in finance. From theory to practice
- Modelling Asset Prices for Algorithmic and High-Frequency Trading
Cites work
- A fully discrete semi-Lagrangian scheme for a first order mean field game problem
- A Mean Field Game Approach to Equilibrium Pricing with Market Clearing Condition
- A mean field game price model with noise
- A mean-field game approach to price formation
- A primer on monotone operator methods
- A Random-Supply Mean Field Game Price Model
- An extended mean field game for storage in smart grids
- Augmented Lagrangian methods for transport optimization, mean field games and degenerate elliptic equations
- Convergence analysis of machine learning algorithms for the numerical solution of mean field control and games. I: The ergodic case
- Deep learning: an introduction for applied mathematicians
- Equilibrium price formation with a major player and its mean field limit
- Finite mean field games: fictitious play and convergence to a first order continuous mean field game
- scientific article; zbMATH DE number 2107836 (Why is no real title available?)
- scientific article; zbMATH DE number 880269 (Why is no real title available?)
- scientific article; zbMATH DE number 7689517 (Why is no real title available?)
- Implicit Functions and Solution Mappings
- Mean field games: numerical methods
- Metric regularity and stability of optimal control problems for linear systems
- Numerical methods for mean field games based on Gaussian processes and Fourier features
- On the metric regularity of affine optimal control problems
- Optimal generation and trading in solar renewable energy certificate (SREC) markets
- Price dynamics for electricity in smart grid via mean-field-type games
- Price formation and optimal trading in intraday electricity markets
- Proximal methods for stationary mean field games with local couplings
- Pseudospectral methods and iterative solvers for optimization problems from multiscale particle dynamics
- Recurrent neural networks for stochastic control problems with delay
- ReLU deep neural networks and linear finite elements
- Stability and sensitivity of solutions to nonlinear optimal control problems
- The deep Ritz method: a deep learning-based numerical algorithm for solving variational problems
- The entry and exit game in the electricity markets: a mean-field game approach
- Value-Gradient Based Formulation of Optimal Control Problem and Machine Learning Algorithm
Cited in
(5)- Estimating permanent price impact via machine learning
- Recent developments in machine learning methods for stochastic control and games
- A fully-discrete semi-Lagrangian scheme for a price formation MFG model
- Title not available (Why is no real title available?)
- Title not available (Why is no real title available?)
This page was built for publication: Machine learning architectures for price formation models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6166250)
