[Quantra Quantinsti] Trading with Machine Learning: Regression + Classification and SVM

[Quantra Quantinsti] Trading with Machine Learning: Regression + Classification and SVM

Трейдинг с помощью машинного обучения: регрессия + классификация и SVM (на Python)
(Trading with Machine Learning: Regression + Classification and SVM)​

Видеокурс на англ. языке + англ. субтитры + исходный код на Python. Ниже представлен перевод описания курса на русский язык и его оригинальное описание на английском (под спойлером).

Данные 2 курса помогут вам понять применение прогнозных моделей машинного обучения на основе регрессии и классификации и дадут вам возможность создавать торговые алгоритмы, основанные на регрессии и опорных векторов (SVM).

В КУРСЕ ВЫ ИЗУЧИТЕ

• Реализацию концепции регрессии с помощью машинного обучения в своей торговле
• Математические понятия, лежащие в основе функции регрессии, такие как градиентный спуск и оптимизация функции стоимости
• Как построить собственную модель регрессии машинного обучения
• Как оптимизировать вашу модель путем решения проблем Bias и Variance
• Прогноз цен на золото ETF путем предварительной обработки данных, добавления гиперпараметров и перекрестной проверки модели
• Решение реальных торговых проблемы с помощью концепций машинного обучения
• Создание торговых алгоритмов, которые можно адаптировать к условиям реального рынка
• Применение методов предварительной обработки данных для обеспечения подачу качественных данных в качестве входных данных в ваш классификатор машинного обучения
• Создание контролируемых классификаторов, таких как классификатор логистической регрессии и классификатор векторов поддержки в Python, и включение их в торговые стратегии
• Понимание различных гиперпараметров, используемых для оптимизации алгоритмов
• Тестирование торговых стратегий и оценка их прибыльности

Спойлер: ОРИГИНАЛЬНОЕ ОПИСАНИЕ НА АНГЛИЙСКОМ

These 2 courses will help you understand the application of Machine Learning Regression and Classification Predictive Models and give you an opportunity to code trading algorithms based on the concepts of Regression and Support Vector Classifier (SVM).

HIGHLIGHTS OF THE COURSE ARE:

• How Machine Learning is changing the trading domain
• Various data pre-processing concepts to increase the performance of a system
• Concept of Hyperparameters and cross validation techniques to get better results out of your trading model
• Concept of regression and the mathematics behind it
• Problems faced in fitting a regression function to a dataset and troubleshoot the Bias and Variance to increase the efficiency of your trading model
• To interpret the prediction made by machine learning algorithms to create a trading strategy
• Code all the concepts learnt to form your strategies in Python
• Machine Learning Classification model and different types of the classifiers
• Binary Classification and the mathematical concepts behind classification
• Logistic Regression Classifier
• Multiclass Classification and the difference between binary and multiclass classification
• One vs all algorithm, one hot encoding, and Softmax Function to perform multiclass classification
• Different performance measure in Machine learning
• Support Vector Machine and the mathematics behind Support Vector Machine
• Different SVM parameters to optimize the model
• To interpret the prediction and create a trading strategy using Support Vector Classifier algorithm
• To predict the trend using Support vector classifier

WHAT WILL YOU LEARN

• Implement concepts of machine learning regression in your trading
• Mathematical concepts behind regression function, such as the gradient descent and cost function optimization
• How to build your own machine learning regression model
• How to optimize your model by troubleshooting Bias and Variance
• Forecast Gold ETF prices by pre-processing the data, adding Hyperparameters and cross validating the model
• Solve real-world trading problems with the help of machine learning concepts
• Create trading algorithms which can adapt to live market conditions
• Apply data preprocessing techniques to ensure quality data is fed as input to your machine learning classifier
• Build supervised classifiers such as logistic regression classifier and support vector classifier in Python and incorporate them in trading strategies
• Understand the different hyperparameters used for optimizing algorithms
• Backtest trading strategies and evaluate their profitabilities

COURSE MODULES

• Problem Statement
• Intro to Data Generation
• Data Pre-Processing
• Regression
• Bias and Variance
• Applying the Prediction
• Creating the Algorithm
• Introduction to Classification and SVM
• Binary Classification
• Multiclass Classification
• Support Vector Machine
• Prediction and Strategy

ABOUT THE AUTHOR
QuantInsti® is a pioneering algorithmic and quantitative trading research institute with a registered user base in 150+ countries. Their flagship course, Executive Programme in Algorithmic Trading (EPAT™) is world’s first verified certification, offered to professionals looking to enter or grow in the algorithmic and quantitative trading industry. QuantInsti also launched its interactive self-paced learning portal, Quantra, offering 20+ interactive courses and tools for quant, created under the guidance of successful practitioners.
With the vision of becoming a global knowledge and technology powerhouse in the quantitative and algorithmic trading domain, QuantInsti also launched Quantra Blueshift in 2018 to offer backtesting and research capabilities for users in both Indian and US markets with minute level data. They work closely with top global financial and educational institutions through their content, delivery and research tools.

===Все курсы по алготрейдингу на Python от Quantra Quantinsti===