# Deep Calibration of Market Simulations using Neural Density Estimators and Embedding Networks

arXiv: https://arxiv.org/abs/2311.11913 · HTML: https://mlsanity.com/paper/2311.11913/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 46 references that are in the map.
- First posted on arXiv 20 Nov 2023.

## Builds on (most cited first, 18 of 18)

- [Masked Autoregressive Flow for Density Estimation](https://mlsanity.com/paper/1705.07057/) (2017)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [The frontier of simulation-based inference](https://mlsanity.com/paper/1911.01429/) (2019)
- [Learning Robust Statistics for Simulation-based Inference under Model Misspecification](https://mlsanity.com/paper/2305.15871/) (2023)
- [Investigating the Impact of Model Misspecification in Neural Simulation-based Inference](https://mlsanity.com/paper/2209.01845/) (2022)
- [Get Real: Realism Metrics for Robust Limit Order Book Market Simulations](https://mlsanity.com/paper/1912.04941/) (2019)
- [ABIDES-Gym: Gym Environments for Multi-Agent Discrete Event Simulation and Application to Financial Markets](https://mlsanity.com/paper/2110.14771/) (2021)
- [A Data-driven Market Simulator for Small Data Environments](https://mlsanity.com/paper/2006.14498/) (2020)
- [ABIDES: Towards High-Fidelity Market Simulation for AI Research](https://mlsanity.com/paper/1904.12066/) (2019)
- [Towards Realistic Market Simulations: a Generative Adversarial Networks Approach](https://mlsanity.com/paper/2110.13287/) (2021)
- [Neural Density Estimation and Likelihood-free Inference](https://mlsanity.com/paper/1910.13233/) (2019)
- [Neural Stochastic Agent-Based Limit Order Book Simulation: A Hybrid Methodology](https://mlsanity.com/paper/2303.00080/) (2023)
- [Graph-Based Learning for Stock Movement Prediction with Textual and Relational Data](https://mlsanity.com/paper/2107.10941/) (2021)
- [Towards Closing the Sim-to-Real Gap in Collaborative Multi-Robot Deep Reinforcement Learning](https://mlsanity.com/paper/2008.07875/) (2020)
- [Efficient Calibration of Multi-Agent Simulation Models from Output Series with Bayesian Optimization](https://mlsanity.com/paper/2112.03874/) (2021)
- [Learning who is in the market from time series: market participant discovery through adversarial calibration of multi-agent simulators](https://mlsanity.com/paper/2108.00664/) (2021)
- [Graph-informed simulation-based inference for models of active matter](https://mlsanity.com/paper/2304.06806/) (2023)

## Built on by (most cited first, 4 of 4)

- [MarS: a Financial Market Simulation Engine Powered by Generative Foundation Model](https://mlsanity.com/paper/2409.07486/) (2024)
- [Right Place, Right Time: Market Simulation-based RL for Execution Optimisation](https://mlsanity.com/paper/2510.22206/) (2025)
- [Keeping Score: Adaptive, Tuning-Free Loss Weighting for Score-Augmented Neural Ratio Estimation](https://mlsanity.com/paper/2605.12118/) (2026)
- [LOB-ID: Evaluating Synthetic Market Data by Inception Distances](https://mlsanity.com/paper/2608.13082/) (2026)

## Abstract (arXiv)

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.