Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks
Authors:
- Namid R. StillmanNSNamid R. Stillman
- Rory BaggottRBRory Baggott
- Justin LyonJLJustin Lyon
- Jianfei ZhangJZJianfei Zhang
- Dingqiu ZhuDZDingqiu Zhu
- Tao ChenTCTao Chen
- Perukrishnen VytelingumPVPerukrishnen Vytelingum
Preprint
Abstract
The ability to construct a realistic simulator of financial exchanges, including reproducing the dynamics of the limit order book, can give insight into many counterfactual scenarios, such as a flash crash, a margin call, or changes in macroeconomic outlook. In recent years, agent-based models have been developed that reproduce many features of an exchange, as summarised by a set of stylised facts and statistics. However, the ability to calibrate simulators to a specific period of trading remains an open challenge. In this work, we develop a novel approach to the calibration of market simulators by leveraging recent advances in deep learning, specifically using neural density estimators and embedding networks. We demonstrate that our approach is able to correctly identify high probability parameter sets, both when applied to synthetic and historical data, and without reliance on manually selected or weighted ensembles of stylised facts.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- Black-box Bayesian inference for agent-based modelsJournal of Economic Dynamics and Control, 2024
- Simulation-based inference in particle physicsNature Reviews Physics, 2021
- The frontier of simulation-based inferenceProceedings of the National Academy of Sciences, 2020
- Normalizing Flows: An Introduction and Review of Current MethodsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
- DeepLOB: Deep Convolutional Neural Networks for Limit Order BooksIEEE Transactions on Signal Processing, 2019
- The Microstructure of the “Flash Crash”: Flow Toxicity, Liquidity Crashes, and the Probability of Informed TradingThe Journal of Portfolio Management, 2011
- Stylized facts of return series, robust estimates and three popular models of volatilityApplied Financial Economics, 2010
- Multi-agent-based Order Book Model of financial marketsEurophysics Letters, 2006
- More stylized facts of financial markets: leverage effect and downside correlationsPhysica A: Statistical Mechanics and its Applications, 2001
- Econophysics: financial time series from a statistical physics point of viewPhysica A: Statistical Mechanics and its Applications, 2000