更智能的交易策略会赢吗？交互交易策略：一种基于代理的方法

IF 0.9 Q4 BUSINESS

Journal of Intelligence Studies in Business Pub Date : 2023-03-09 DOI:10.37380/jisib.v12i3.929

Hidayet Beyhan, Burç Ulengin

{"title":"更智能的交易策略会赢吗？交互交易策略：一种基于代理的方法","authors":"Hidayet Beyhan, Burç Ulengin","doi":"10.37380/jisib.v12i3.929","DOIUrl":null,"url":null,"abstract":"An artificial financial market is built on top of the Genoa Artificial Stock Market. The market is populated with agents having different trading strategies and they are let to interact with each other. Agents differ in the trading method they use to trade, and they are grouped as noise, technical, statistical analysis, and machine learning traders. The model is validated by the replication of stylized facts in financial asset returns. We were able to replicate the leptokurtic shape of the probability density function, volatility clustering, and the absence of autocorrelation in asset returns. The wealth dynamics for each agent group are analyzed throughout the trading period. Agents with a higher time complexity trading strategy outperform those with a strategy comparing their final wealth.","PeriodicalId":43580,"journal":{"name":"Journal of Intelligence Studies in Business","volume":null,"pages":null},"PeriodicalIF":0.9000,"publicationDate":"2023-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Does more intelligent trading strategy win? Interacting trading strategies: an agent-based approach\",\"authors\":\"Hidayet Beyhan, Burç Ulengin\",\"doi\":\"10.37380/jisib.v12i3.929\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"An artificial financial market is built on top of the Genoa Artificial Stock Market. The market is populated with agents having different trading strategies and they are let to interact with each other. Agents differ in the trading method they use to trade, and they are grouped as noise, technical, statistical analysis, and machine learning traders. The model is validated by the replication of stylized facts in financial asset returns. We were able to replicate the leptokurtic shape of the probability density function, volatility clustering, and the absence of autocorrelation in asset returns. The wealth dynamics for each agent group are analyzed throughout the trading period. Agents with a higher time complexity trading strategy outperform those with a strategy comparing their final wealth.\",\"PeriodicalId\":43580,\"journal\":{\"name\":\"Journal of Intelligence Studies in Business\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.9000,\"publicationDate\":\"2023-03-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Intelligence Studies in Business\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.37380/jisib.v12i3.929\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"BUSINESS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Intelligence Studies in Business","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.37380/jisib.v12i3.929","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"BUSINESS","Score":null,"Total":0}

引用次数: 0

摘要

在热那亚人工股票市场的基础上，建立了一个人工金融市场。市场上充斥着拥有不同交易策略的代理人，他们可以相互交流。经纪人使用不同的交易方法进行交易，他们被分为噪音交易者、技术交易者、统计分析交易者和机器学习交易者。该模型通过在金融资产回报中复制程式化事实来验证。我们能够复制概率密度函数的细峰形状，波动性聚类，以及资产回报中不存在自相关。在整个交易期间，分析了每个代理组的财富动态。具有较高时间复杂度交易策略的代理人比具有比较最终财富策略的代理人表现更好。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Does more intelligent trading strategy win? Interacting trading strategies: an agent-based approach

An artificial financial market is built on top of the Genoa Artificial Stock Market. The market is populated with agents having different trading strategies and they are let to interact with each other. Agents differ in the trading method they use to trade, and they are grouped as noise, technical, statistical analysis, and machine learning traders. The model is validated by the replication of stylized facts in financial asset returns. We were able to replicate the leptokurtic shape of the probability density function, volatility clustering, and the absence of autocorrelation in asset returns. The wealth dynamics for each agent group are analyzed throughout the trading period. Agents with a higher time complexity trading strategy outperform those with a strategy comparing their final wealth.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Journal of Intelligence Studies in Business BUSINESS-

CiteScore

2.00

自引率

11.10%

发文量

审稿时长

8 weeks

期刊介绍： The Journal of Intelligence Studies in Business (JISIB) is a double blinded peer reviewed open access journal published by Halmstad University, Sweden. Its mission is to help facilitate and publish original research, conference proceedings and book reviews. The journal includes articles within areas such as Competitive Intelligence, Business Intelligence, Market Intelligence, Scientific and Technical Intelligence, Collective Intelligence and Geo-economics. This means that the journal has a managerial as well as an applied technical side (Information Systems), as these are now well integrated in real life Business Intelligence solutions. By focusing on business applications the journal do not compete directly with journals of Library Sciences or State or Military Intelligence Studies. Topics within the selected study areas should show clear practical implications.