当前位置:网站首页>What are the basic steps to develop a quantitative trading strategy?
What are the basic steps to develop a quantitative trading strategy?
2022-08-10 00:13:00 【Q1841085904】
The first step is to build logic with ready-made indicators
The software has many built-in technical indicators, take out one, write the trading point, and back-test the historical market, so that you can get a simple strategy.With the accumulation of strategic experience, the logical choices here will become more and more diverse.
Of course such a strategy is generally not profitable.
The second step is to optimize parameters
Select parameter traversal and observe how different parameters affect the strategy.In general, we will get several sets of parameters that seem to be more profitable.
The third step, out-of-sample testing
For example, the parameters we traversed before were the data of 2016, and several parameters with good performance were obtained, then we will use the data of 2014/2016 to test these parameters.Generally speaking, this parameter will be bleak outside the sample, and it will not be as powerful as the optimization in the sample.
The fourth step, observation to determine what is the reason for the failure of the strategy
Assume that the reason for the failure of the strategy is that one or two special market conditions outside the sample lead to large losses, then we can set a hard stop loss to avoid this risk; if we find that the failure of the strategy is due to too few transactions, then weJust relax the transaction logic a little, such as changing the place where >x is required to >=x or even >=x-1.Wait, this modification is the experience of the strategy.
边栏推荐
猜你喜欢
注意力引导网络用于视网膜图像分割
Transfer Learning & Kemin Initialization
【服务器数据恢复】SAN LUN映射出错导致文件系统数据丢失的数据恢复案例
Space not freed after TRUNCATE table
Kubernetes Service对象
开发者必备:一文快速熟记【数据库系统】和【软件开发模型】常用知识点
[Microservice~Nacos] Nacos service provider and service consumer
Flask introductory learning tutorial
Bi Sheng Compiler Optimization: Lazy Code Motion
shell数组
随机推荐
leetcode brush questions diary Calculate the number of elements on the right that is less than the current element
R语言检验时间序列的平稳性:使用tseries包的adf.test函数实现增强的Dickey-Fuller(ADF)检验、检验时序数据是否具有均值回归特性(平稳性)、不具有均值回归特性的案例
Qt 消息机制和事件
Under the NVM node installation;The node environment variable configuration
chart.js面积图曲线图统计插件
C. Mere Array
量化交易接口系统有哪些稳定性?
Qt message mechanism and events
C 在函数声明前加typedef
R语言将列表数据转化为向量数据(使用unlist函数将列表数据转化为向量数据)
leetcode:319. 灯泡开关
Flask's routing (app.route) detailed
Evolution of MLOps
xctf攻防世界 Web高手进阶区 shrine
leetcode:331. 验证二叉树的前序序列化
关于ETL的两种架构(ETL架构和ELT架构)
如何坚持使用程序化系统?
R语言使用mean函数计算样本(观测)数据中指定变量的相对频数:计算时间序列数据中大于前一个观测值的观测值所占的比例总体的比例
leetcode 38. 外观数列
Activiti7审批流