|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/machine-learning-applied-to-stock-crypto-trading-python/
课程评论：没有评论
课程名称：机器学习在股票和加密货币交易中的应用 - Python 课程概述： 本课程旨在通过使用Python部署机器学习技术来分析金融数据，帮助您在金融交易中获得优势。在课程中，您将学习到： - 利用隐马尔可夫模型发现隐藏的市场状态和机制。 - 运用K均值聚类客观地对类似的交易所交易基金（ETF）进行分组，以便进行配对交易，并理解如何利用协整和Z得分等统计方法进行盈利。 - 通过包含大量技术指标并使用主成分分析（PCA）提炼有效信息，预测恐慌指数（VIX）的变化。 - 使用先进的机器学习算法XGBOOST，对比特币价格数据进行未来趋势预测。 - 评估模型性能，以增强对预测结果的信心。 - 通过量化测试数据的准确性、精确率、召回率和F1分数，推断您的潜在交易优势。 - 开发一个简单的AI模型交易正弦波，并进一步学习如何完全自主交易苹果股票，而不需要任何选股提示。 - 构建用于分类的深度学习神经网络，并获取使用长短期记忆（LSTM）神经网络对序列数据进行预测的代码。 - 使用Python库，如Pandas、PyTorch（用于深度学习）、sklearn等。 本课程并不涉及深入的理论知识，而是纯粹以实践为主，理论部分高层次，容易理解基本概念，尤其是其应用，使您可以立即付诸实践。如果您在寻找含有大量数学内容的课程，这可能不是适合您的选择。但如果您希望以一种有趣、刺激和潜在盈利的方式体验使用金融数据的机器学习，那么这门课程将非常适合您。
Gain an edge in financial trading through deploying Machine Learning techniques to financial data using Python. In this course, you will:Discover hidden market states and regimes using Hidden Markov Models.Objectively group like-for-like ETF's for pairs trading using K-Means Clustering and understand how to capitalise on this using statistical methods like Cointegration and Zscore.Make predictions on the VIX by including a vast amount of technical indicators and distilling just the useful information via Principle Component Analysis (PCA).Use one of the most advanced Machine Learning algorithms, XGBOOST, to make predictions on Bitcoin price data regarding the future.Evaluate performance of models to gain confidence in the predictions being made.Quantify objectively the accuracy, precision, recall and F1 score on test data to infer your likely percentage edge.Develop an AI model to trade a simple sine wave and then move on to learning to trade the Apple stock completely by itself without any prompt for selection positions whatsoever. Build a Deep Learning neural network for both Classification and receive the code for using an LSTM neural network to make predictions on sequential data.Use Python libraries such as Pandas, PyTorch (for deep learning), sklearn and more.This course does not cover much in-depth theory. It is purely a hands-on course, with theory at a high level made for anyone to easily grasp the basic concepts, but more importantly, to understand the application and put this to use immediately.If you are looking for a course with a lot of math, this is not the course for you.If you are looking for a course to experience what machine learning is like using financial data in a fun, exciting and potentially profitable way, then you will likely very much enjoy this course.
