A Review of Recent Artificial Market Simulation Studies for Financial Market Regulations And/Or Rules

Mizuta, Takanobu

doi:10.2139/ssrn.2710495

Cited by 20 publications

(18 citation statements)

References 113 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Financial market simulation has been used for investigating market microstructure (Muranaga et al 1999) and financial market regulations (Mizuta 2016). In particular, multi agent financial market simulation (LeBaron et al 2001;Lux and Marchesi 1999;Samanidou et al 2007) is commonly used.…”

Section: Financial Market Simulationmentioning

confidence: 99%

Deep Reinforcement Learning in Agent Based Financial Market Simulation

Maeda

deGraw²,

Kitano

et al. 2020

JRFM

View full text Add to dashboard Cite

Prediction of financial market data with deep learning models has achieved some level of recent success. However, historical financial data suffer from an unknowable state space, limited observations, and the inability to model the impact of your own actions on the market can often be prohibitive when trying to find investment strategies using deep reinforcement learning. One way to overcome these limitations is to augment real market data with agent based artificial market simulation. Artificial market simulations designed to reproduce realistic market features may be used to create unobserved market states, to model the impact of your own investment actions on the market itself, and train models with as much data as necessary. In this study we propose a framework for training deep reinforcement learning models in agent based artificial price-order-book simulations that yield non-trivial policies under diverse conditions with market impact. Our simulations confirm that the proposed deep reinforcement learning model with unique task-specific reward function was able to learn a robust investment strategy with an attractive risk-return profile.

show abstract

Section: Financial Market Simulationmentioning

confidence: 99%

Deep Reinforcement Learning in Agent Based Financial Market Simulation

Maeda

deGraw²,

Kitano

et al. 2020

JRFM

View full text Add to dashboard Cite

show abstract

“…Mizuta [11] reviewed other previous agent-based models for designing a financial market that works well that are not mentioned above.…”

Section: An Artificial Market Model = An Agent-based Model For a Finamentioning

confidence: 99%

“…A PTS is very similar to an Alternative Trading System (ATS) and Electronic Communications Network (ECN) in other countries. 11 Mizuta et al used the data from the Tokyo Stock Exchange to calculate ∆P and σt. They used Bloomberg data to calculate the market share or trading volume of the PTS, which is its entire trading volume divided by those of Japans traditional stock exchanges and PTS, where PTSs are Japan Next PTS J-Market, Japan Next PTS X-Market, and Chi-X Japan PTS, and where Japans traditional stock exchanges are the Tokyo, Osaka, Nagoya, Fukuoka, and Sapporo stock exchanges and JASDAQ.…”

Section: Summary Of the Case Study: Tick Size Reductionmentioning

confidence: 99%

An Agent-Based Model for Designing a Financial Market That Works Well

Mizuta¹

2019

SSRN Journal

Self Cite

View full text Add to dashboard Cite

Designing a financial market that works well is very important for developing and maintaining an advanced economy, but is not easy because changing detailed rules, even ones that seem trivial, sometimes causes unexpected large impacts and side effects. A computer simulation using an agent-based model can directly treat and clearly explain such complex systems where micro processes and macro phenomena interact. Many effective agent-based models investigating human behavior have already been developed. Recently, an artificial market model, which is an agent-based model for a financial market, has started to contribute to discussions on rules and regulations of actual financial markets. I introduce an artificial market model to design financial markets that work well and describe a previous study investigating tick size reduction. I hope that more artificial market models will contribute to designing financial markets that work well to further develop and maintain advanced economies.1 Sabzian et al. provide a comprehensive review of agentbased models for complex systems [3].

show abstract

“…In many previous artificial market studies, the models were verified to see whether they could explain stylized facts, such as a fat tail or volatility clustering (LeBaron 2006;Chen et al 2012;Mizuta 2016;Todd et al 2016). A fat tail means that the kurtosis of price returns is positive.…”

Section: Verification Of Modelmentioning

confidence: 99%

“…These are strong advantages for an artificial market simulation. The effects of the distribution and several changing regulations have been investigated using artificial market simulations (LeBaron 2006;Chen et al 2012;Mizuta 2016;Todd et al 2016).…”

Section: Introductionmentioning

confidence: 99%

Mechanism by which active funds make market efficient investigated with agent-based model

Mizuta

Horie

2018

Evolut Inst Econ Rev

Self Cite

View full text Add to dashboard Cite

Since active managed funds, in which a manager chooses stocks expected to rise in price, invest on the basis of the intrinsic fundamental value of companies, they discover the fundamental price and make market prices converge with the fundamental price (make a market efficient); therefore, they play an important role in allocating capital, which is an important function in capitalism. A previous empirical study showed active funds that trade infrequently, "patient" active funds, earn more. At first glance, what patient active funds trade infrequently seems inconsistent with making a market efficient. In this study, we modeled agents who reflect the characteristics of patient active funds that trade infrequently and "impatient" active funds that trade frequently. We succeeded in figuring out the mechanism of how patient and impatient funds impacted market prices and in proving that what patient active funds trade infrequently is not inconsistent with making a market efficient. Concretely, the simulation results indicated that patient active funds trade frequently only in the rare situation that a market became unstable and inefficient. These trades, occurring only at a necessary time, impact market prices and lead them to converge with the fundamental price. The results also indicated that patient active funds earn less not so much because of a more efficient market, but because the market is too inefficient, so changes in price formation due to trades of impatient active funds reduce the chance that patient active funds will realize profit. KeywordsAgent-based model • Multi-agent simulation • Artificial market simulation • Active managed fund • Passive managed fund • Index fund • Market efficiency • Price discovery function The opinions contained herein are solely those of the authors and do not necessarily reflect those of SPARX Asset Management Co., Ltd.

show abstract

A Review of Recent Artificial Market Simulation Studies for Financial Market Regulations And/Or Rules

Cited by 20 publications

References 113 publications

Deep Reinforcement Learning in Agent Based Financial Market Simulation

Deep Reinforcement Learning in Agent Based Financial Market Simulation

An Agent-Based Model for Designing a Financial Market That Works Well

Mechanism by which active funds make market efficient investigated with agent-based model

Contact Info

Product

Resources

About