检索规则说明:AND代表“并且”;OR代表“或者”;NOT代表“不包含”;(注意必须大写,运算符两边需空一格)
检 索 范 例 :范例一: (K=图书馆学 OR K=情报学) AND A=范并思 范例二:J=计算机应用与软件 AND (U=C++ OR U=Basic) NOT M=Visual
作 者:熊熊[1] 张博洋[1] 张永杰[1] 付琳惠[1]
机构地区:[1]天津大学管理与经济学部
出 处:《科学决策》2013年第8期1-15,共15页Scientific Decision Making
基 金:国家自然科学基金项目(项目编号:71271145;71131007);教育部新世纪优秀人才支持计划项目(项目编号:NCET-07-0605);教育部创新团队发展计划(项目编号:IRT1028)
摘 要:随着国内金融市场的不断发展与完善,程序化交易变得越来越受关注。目前国内大多数程序化交易者并没有建立起一个完备的检测与优化体系,采取的测试方式大多为简单的历史数据回溯测试,这容易导致对历史数据曲线的过度拟合。论文构造出一个较完整的程序化交易系统的检测与优化体系,依次分为六个步骤:设计交易策略,交易策略程式化,验证性检测,交易系统最优化,推进的样本外测试,实战交易。通过此体系可以分析交易模型的风险与收益水平及策略的稳定性,并得出健全的交易策略需具备的特点:获利相对均匀分布、具有相对稳定的盈亏次数比率、具有连续且平滑的最优化参数集、适应不同类型的市场且风险可控。With the continuous development of the domestic financial market, program trading has received more and more attention. At present, most domestic program traders have not established a complete system of testing and optimization. Most of them just uses the method of backtesting instead, which can easily lead to excessive of historical data curve overfitting, but the overfitting is not equal to optimization. This paper innovative constructed a relatively complete system, including six process, design trading strategy, strategy programming, preliminary testing, optimiza- tion,step-forward analysis, trading. Through this system we can get the degree of the risk of trading model and the stability of strategy, as well as the key element of the sound trading strate- gy, relatively uniform distribution of profit, relatively stable ratio of the times of gains and losses, a group of continuous and smooth optimal parameters set, adaptability in different types of markets and the risk can be controlled.
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在载入数据...
正在链接到云南高校图书馆文献保障联盟下载...
云南高校图书馆联盟文献共享服务平台 版权所有©
您的IP:216.73.216.106