Skip to content
All library documents

Calibrating an Agent-Based Intraday Market Model with XGBoost

Article arXiv papers · Author: Kang Gao et al.
Read the original

Summary

The article introduces XGB-Chiarella, a method for calibrating an extended Chiarella agent-based market model to reproduce intraday price behavior. The simulated market contains fundamental, momentum, and noise traders. Instead of estimating model parameters with the original Expectation-Maximisation approach, the method uses an XGBoost surrogate as an efficient proxy for the agent-based simulation.

The authors report that the surrogate approximates the simulation and that its calibration better matches historical stylized facts than the original parameter-estimation method. They also report generating realistic price series for stocks from three exchanges, with one agent per trader category sufficient at the studied minute-level scale. These findings concern the model and calibration described in the article; the summary provides no detailed validation metrics or evidence that the generated prices predict future returns. The authors suggest the framework may help practitioners examine price formation and risk management.

Key ideas

  • The extended Chiarella model represents fundamental, momentum, and noise traders.
  • An XGBoost surrogate is used to calibrate the agent-based simulation.
  • The paper reports better agreement with historical stylized facts than the original estimation approach.
  • The model is applied to stocks from three exchanges at a minute-level timescale.
  • The reported price realism does not by itself demonstrate predictive trading value.

Tags

EquitiesMachine learningMarket microstructureRisk managementStatistics
Full text
# 2208.14207


# Understanding intra-day price formation process by agent-based financial market simulation: calibrating the extended chiarella model









This article presents XGB-Chiarella, a powerful new approach for deploying agent-based models to generate realistic intra-day artificial financial price data. This approach is based on agent-based models, calibrated by XGBoost machine learning surrogate. Following the Extended Chiarella model, three types of trading agents are introduced in this agent-based model: fundamental traders, momentum traders, and noise traders. In particular, XGB-Chiarella focuses on configuring the simulation to accurately reflect real market behaviours. Instead of using the original Expectation-Maximisation algorithm for parameter estimation, the agent-based Extended Chiarella model is calibrated using XGBoost machine learning surrogate. It is shown that the machine learning surrogate learned in the proposed method is an accurate proxy of the true agent-based market simulation. The proposed calibration method is superior to the original Expectation-Maximisation parameter estimation in terms of the distance between historical and simulated stylised facts. With the same underlying model, the proposed methodology is capable of generating realistic price time series in various stocks listed at three different exchanges, which indicates the universality of intra-day price formation process. For the time scale (minutes) chosen in this paper, one agent per category is shown to be sufficient to capture the intra-day price formation process. The proposed XGB-Chiarella approach provides insights that the price formation process is comprised of the interactions between momentum traders, fundamental traders, and noise traders. It can also be used to enhance risk management by practitioners.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.