Get real: realism metrics for robust limit order book market simulations

Get real: realism metrics for robust limit order book market simulations
复制标题

变得真实:稳健的限价订单簿市场模拟的现实指标

DOI:
10.1145/3383455.3422561
复制
发表时间:
2020
期刊:
ICAIF '20: Proceedings of the First ACM International Conference on AI in Finance
影响因子:
--
通讯作者:
Balch, Tucker
Balch, Tucker
中科院分区:
--
文献类型:
--
作者:
Vyetrenko, Svitlana;Byrd, David;Petosa, Nick;Mahfouz, Mahmoud;Dervovic, Danial;Veloso, Manuela;Balch, Tucker

文献摘要

参考文献

被引文献

相似文献

市场模拟是一种越来越重要的评估和培训交易策略以及测试“假设”情景的方法。这些模拟结果的可信度取决于测试策略的环境现实程度。作为一个步骤,为现实的模拟市场提供基准,我们列举了可衡量的程式化事实的限价订单簿(LOB)市场在多个资产类别的文献。我们将这些指标应用于来自真实的市场的数据,并将结果与来自模拟市场的数据进行比较。我们说明了他们的使用在五个不同的模拟市场配置:第一(市场重放)是经常在实践中使用,以评估交易策略,其他四个是基于交互式代理的模拟(IABS)配置,联合收割机零智能代理,代理有限的战略行为。这些模拟代理依赖于为资产提供基本价值的内部“oracle”。在传统的IABS方法的基本来源于平均回复随机游走。我们表明,市场表现出更现实的行为时,基本面来自历史市场数据。我们进一步实验说明了IABS技术的有效性,而不是市场重放。
Market simulation is an increasingly important method for evaluating and training trading strategies and testing "what if" scenarios. The extent to which results from these simulations can be trusted depends on how realistic the environment is for the strategies being tested. As a step towards providing benchmarks for realistic simulated markets, we enumerate measurable stylized facts of limit order book (LOB) markets across multiple asset classes from the literature. We apply these metrics to data from real markets and compare the results to data originating from simulated markets. We illustrate their use in five different simulated market configurations: The first (market replay) is frequently used in practice to evaluate trading strategies; the other four are interactive agent based simulation (IABS) configurations which combine zero intelligence agents, and agents with limited strategic behavior. These simulated agents rely on an internal "oracle" that provides a fundamental value for the asset. In traditional IABS methods the fundamental originates from a mean reverting random walk. We show that markets exhibit more realistic behavior when the fundamental arises from historical market data. We further experimentally illustrate the effectiveness of IABS techniques as opposed to market replay.
零智能加模型能否解释金融时间序列数据的程式化事实?
DOI: --
发表时间: 2012
期刊: Adaptive Agents and Multi-Agent Systems
影响因子: --
作者:
Imon Palit;S. Phelps;W. Ng
通讯作者: W. Ng
基于代理的金融市场建设者指南
DOI: 10.1088/1469-7688/1/2/307
发表时间: 2001
影响因子: 1.3
作者:
B. LeBaron
通讯作者: B. LeBaron
DOI: 10.2139/ssrn.98068
发表时间: 1998
期刊: Derivatives eJournal
影响因子: --
作者:
Giuseppe Ballocchi;C. Hopman;M. Dacorogna;Ulrich A. Müller;R. Olsen
通讯作者: R. Olsen
DOI: 10.2139/ssrn.1932152
发表时间: 2011
期刊: 2012 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr)
影响因子: --
作者:
M. Paddrik;Roy Hayes;Andrew Todd;Steve Y. Yang;P. Beling;W. Scherer
通讯作者: W. Scherer
DOI: 10.1016/j.jedc.2017.01.014
发表时间: 2017-04-01
影响因子: 1.9
作者:
Grazzini, Jakob;Richiardi, Matteo G.;Tsionas, Mike
通讯作者: Tsionas, Mike