|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/algorithmic-trading-with-python/
课程评论：没有评论
**Coursera 课程摘要：使用 Python 实战算法交易** 本课程将带您从零开始构建自己的量化回测系统，并结合 Plotly 库进行可视化展示。我们将主要运用指数移动平均线 (EMA)、移动平均收敛散度 (MACD)、布林带 (Bollinger Band)、布林带结合 ADX 指标以及三重 EMA 通道等技术指标进行回测。 课程将重点介绍如何使用 pandas 和 DataFrame 处理海量时间序列数据。为了直观地展示回测结果，我们将使用美观且易于理解的 Plotly 库。 在学习回测的过程中，您将掌握多种重要的绩效衡量指标，例如胜率、复合年增长率 (CAGR)、预期收益以及最大回撤。 随后，课程将引导您进行参数优化，并对不同参数下的各项绩效指标进行对比分析。 您将有机会模拟在 NASDAQ100 指数中的股票交易策略，并可以根据您的交易计划加入各种因素，如头寸规模、股票排序、止损、止盈、交易成本以及其他条件。 最后，您将学会构建筛选系统，以便每天都能发现具有潜在买入信号的股票。本课程将为您介绍两种筛选系统：超卖股票筛选和强劲上升趋势股票筛选。当然，您也可以根据自己的交易理念开发自定义的筛选系统。 本课程从 Python 编程基础讲起，确保即使是初学者也能轻松上手，并为您后续的独立开发打下坚实基础。
In this course you will learn to build your own backtesting system from scratch and illustrating with plotly library. We mainly use technical indicator for backtesting such as Exponential Moving Average (EMA), Moving average convergence divergence (MACD), Bollinger Band, Bollinger Band + ADX and 3 EMA channels.We mainly use functions relating to pandas and DataFrame being able to deal with large time-series data. For illustrate result, we use plotly library which is beautiful and easy to understand.During learning backtesting, you will learn many performance measurement. For example, win rate, compound annual growth rate (CAGR) , expected returns and maximum drawdown.Next, you will learn to do parameter optimization and compare many performance measurement in each parameter.You will learn to simulate your strategies with stocks in NASDAQ100 ,also you can add any factors in your trading plan such as position sizing, ranking stocks, cutting loss, taking profit ,transaction cost and other conditions. Lastly, you can make screening system which you can find stocks having interesting buy signals everyday. In this course, I introduce you 2 screening system which are oversold stock and strong uptrend stock. However, you can adapt your trading idea to build your own screening system.Learning python coding in this course is starting from scratch and you can have further developing by yourselves.
