JPX Working Paper Vol.9 【Summary】
Impacts of Speedup of Market System on Price Formations using Artificial Market Simulations
http://www.jpx.co.jp/corporate/news-releases/0010/20150331-02.html
Price Variation Limits and Financial Market Bubbles: Artificial Market Simulations with Agents' Learning Process: presented by Takanobu MIZUTA et. al., EEE Symposium Series on Computational Intelligence, Computational Intelligence for Financial Engineering and Economics (CIFEr), 2013.
Do Dark Pools Stabilize Markets and Reduce Market Impacts? -- Investigations ...Takanobu Mizuta
?
In financial stock markets, dark pools, which never provide any order books and quotes, are becoming widely used. It is said that dark pools may lead to stabilization of markets. However, an increased use of dark pools does raise regulatory concerns as it may ultimately affect the quality of the price discovery mechanism. In this study, we built an artificial market model, multi-agent simulation, including one lit market, which provides all order books to investors, and one dark pool to investigate whether dark pools stabilize markets or not. We found that as the dark pool is increasingly used, markets become more stable. We also found that using the dark pool more reduces the market impacts. However, if other investors' usage rates of dark pools become too large, investors must use the dark pool more than other investors to avoid market impacts. When tick size of a lit market is large, dark pools are more useful to avoid market impacts. These results suggest that dark pools stabilize markets when the usage rate is under some threshold and negatively affect the market when the usage rate is over that threshold. Our simulation results suggested the threshold might be much lager than the usage rate in present real financial markets.
JPX Working Paper Vol.9 【Summary】
Impacts of Speedup of Market System on Price Formations using Artificial Market Simulations
http://www.jpx.co.jp/corporate/news-releases/0010/20150331-02.html
Price Variation Limits and Financial Market Bubbles: Artificial Market Simulations with Agents' Learning Process: presented by Takanobu MIZUTA et. al., EEE Symposium Series on Computational Intelligence, Computational Intelligence for Financial Engineering and Economics (CIFEr), 2013.
Do Dark Pools Stabilize Markets and Reduce Market Impacts? -- Investigations ...Takanobu Mizuta
?
In financial stock markets, dark pools, which never provide any order books and quotes, are becoming widely used. It is said that dark pools may lead to stabilization of markets. However, an increased use of dark pools does raise regulatory concerns as it may ultimately affect the quality of the price discovery mechanism. In this study, we built an artificial market model, multi-agent simulation, including one lit market, which provides all order books to investors, and one dark pool to investigate whether dark pools stabilize markets or not. We found that as the dark pool is increasingly used, markets become more stable. We also found that using the dark pool more reduces the market impacts. However, if other investors' usage rates of dark pools become too large, investors must use the dark pool more than other investors to avoid market impacts. When tick size of a lit market is large, dark pools are more useful to avoid market impacts. These results suggest that dark pools stabilize markets when the usage rate is under some threshold and negatively affect the market when the usage rate is over that threshold. Our simulation results suggested the threshold might be much lager than the usage rate in present real financial markets.
Chapter 13 Artificial Intelligence (AI) for Financial Markets: A Good AI for ...Takanobu Mizuta
?
Chapter 13
Artificial Intelligence (AI) for Financial Markets: A Good AI for Designing Better Financial Markets and a Bad AI for Manipulating Markets
のご紹介
書籍 Digital designs for money, markets, and social designs に収録
スパークス?アセット?マネジメント株式会社
運用調査本部 ファンドマネージャー 兼 上席研究員
水田孝信
本発表資料はスパークス?アセット?マネジメント株式会社の公式見解を表すものではありません.すべては個人的見解であります.
ワークショップ: https://sites.google.com/view/ddmmsd2022/
書籍: https://doi.org/10.1007/978-981-19-0937-5
4-5 May 2022 IEEE Computational Intelligence for Financial Engineering and Economics
Instability of financial markets by optimizing investment strategies investigated by an agent-based model
Takanobu Mizuta SPARX Asset Management Co. Ltd.
Isao Yagi Kogakuin University
Kosei Takashima Nagaoka University
Note that the opinions contained herein are solely those of the authors and do not necessarily reflect those of SPARX Asset Management Co., Ltd.
In this study, we built an artificial market model by adding technical analysis strategy agents (TAs), which search one optimized parameter in a whole simulation run, to the prior model of [mizuta 2016]. The TAs are a momentum TA (TA-m) and reversal TA (TA-r), and we investigated whether investors' inability to accurately estimate market impacts in their optimizations leads to optimization instability.
When both the TA-m and TA-r exist, the parameters of investment strategies were changing irregularly and unexpectedly. This means that even if all other traders are fixed, only one investor optimizing his/her strategy using backtesting leads to the time evolution of market prices becoming unstable. Financial markets are essentially unstable, and naturally, investment strategies are not able to be fixed. The reason is that even when one investor selects a rational strategy at that time, it changes the time evolution of prices, it becomes no longer rational, another strategy becomes rational, and the process repeats.
Optimization instability is one level higher than ``non-equilibrium of market prices.'' Therefore, the time evolution of market prices produced by investment strategies having such unstable parameters is highly unlikely to be predicted and have stable laws written by equations. This nature makes us suspect that financial markets include the principle of natural uniformity and indicates the difficulty of building an equation model explaining the time evolution of prices.
L'intelligence artificielle utilisée sur les marchés financiersTakanobu Mizuta
?
L'intelligence artificielle utilisée sur les marchés financiers
This article was just translated by DeepL from the Japanese article,
https://www.sparx.co.jp/report/special/3202.html
So, sorry for poor French.
Artificial Intelligence Used in Financial MarketsTakanobu Mizuta
?
Artificial Intelligence Used in Financial Markets
This article was just translated by DeepL from the Japanese article,
https://www.sparx.co.jp/report/special/3202.html
So, sorry for poor English.
What is a Hight-Speed Trade? Why does a Stock Exchange Speed-Up?Takanobu Mizuta
?
What is a Hight-Speed Trade? Why does a Stock Exchange Speed-Up?
2021 IEEE 71st Electronic Components and Technology Conference EPS Seminar
Takanobu Mizuta SPARX Asset Management Co., Ltd.
Note that the opinions contained herein are solely those of the authors and do not necessarily reflect those of SPARX Asset Management Co., Ltd.
4. 4444
●●●● 連続連続連続連続ダブルオークションダブルオークションダブルオークションダブルオークション
???? 現実現実現実現実のののの値幅制限値幅制限値幅制限値幅制限をををを実装実装実装実装するのにするのにするのにするのに必要必要必要必要
●●●● エージェントモデルエージェントモデルエージェントモデルエージェントモデルはははは簡素簡素簡素簡素
???? 恣意的恣意的恣意的恣意的なななな結果結果結果結果をををを避避避避けるためけるためけるためけるため “Keep it short and simple”
Chiarella et. al. [2009]
学習過程学習過程学習過程学習過程
人工市場モデル (エージェント?ベースド?モデル)
+ ((((オリジナルオリジナルオリジナルオリジナル))))((((オリジナルオリジナルオリジナルオリジナル))))
??
?
?
??
?
?
++=
∑
t
jj
t
jhjt
f
j
i ji
t
je wrw
P
P
w
w
r ε,3,,2,1
,
, log
1
ファンダメンタル テクニカル ノイズ
予想リターン
↑ 市場混乱の再現に必要
パフォーマンスが良かった戦略 を上げる
パフォーマンスが悪かった戦略 を下げる
,i jw
戦略ウエイト
↑ エージェント
ごとに異なる
,i jw
,i jw
1000体体体体ののののheterogeneousななななエージェントエージェントエージェントエージェント