Applied Machine Learning with R (Trading Use Case) - 2020
What you'll learn
- Understand how to develop a quantitative trading strategy
- how to use machine learning for trading in R
- Learn about different type of machine learning algorithms (Naive Bayes, support vector machines and random Forest) for developing profitable trading strategies
- Learn to write simple and powerful codes in r for quantitative finance
- Understand the difference between trading actors in the market and learn about manual and systematic trading strategies
- How to predict the price direction of any asset class using custom written scripts and algorithms in R
- Use different hyperparameters to improve predictive power of classification based machine learning models
- Learn how to analyse PnL and performance metrics of trading strategies
Requirements
- basic knowledge of trading and finance
- beginner R user
- Awareness of machine learning
Description
The course is designed to fully immerse you into the complete quantitative trading/finance workflow, going from hypothesis generation to data preparation, feature engineering and training testing of multiple machine learning algorithms (backtesting). It is a bootcamp designed to get you from zero to hero using R. The course is aimed at teaching about trading, giving you understanding of the differences between discretionary and quantitative trading. You will learning about different trading instruments/products or also known as asset classes.
Course elements:
Learn about trading and the quantitative trading workflow. Develop a solid understand of what is required to do quantitative trading analysis and the advantages and disadvantages.
Learn how to write simple and complex codes in r with some r refresher lecture. Learn how to use the quantmod package to access/load free market data from yahoo finance and other sources.
Learn how to download futures data from NinjaTrader. Load the data in R and do data preparation and visualization.
Explore various trading ideas/hypothesis on the web, and learn how to generate original trading ideas.
Learn and understand what machine learning is and get a good grip of the type of machine learning algorithms available to solve different type of problems ( namely classification and regression problems).
Code along while learning about feature engineering, write algorithms for training and testing support vector machine, naïve bayes and random forest models and use these to predict the next price direction of crude oil futures. Realize that these strategies can be used for other trading instruments/products.
Compare the model performance and do portfolio selection by only selecting the non correlated models.
Disclaimer
This course is for educational purpose and does not constitute trading or investment advice. All content, teaching material and codes are presented with sharing and learning purpose and with no guarantee of exactness or completeness.
No past performance is indicative of future performance and the trading strategies presented here are based on hypothetical and historical backtesting. Trading futures, forex and options involves the risk of loss. Please consider carefully if trading is appropriate to your financial situation. Only risk capital you can afford to lose, and the risk of loss being substantial, you should consider carefully the inherent risks.
Who this course is for:
- Investment professionals interested to learn to apply classification-based machine learning techniques to investing and trading strategies
- Amateur traders and semi-professional quants looking for original innovative trading and quantitative finance ideas
- Data scientist and enthusiasts interested in different machine learning use cases
- Experienced and beginner R users interested in quantitative analysis/trading using R
- anyone looking for how machine learning can be applied into investing
Instructors
- 3.6 Instructor Rating
- 96 Reviews
- 983 Students
- 2 Courses
Data scientist and passionate about the financial market. I have been trading for the last 3 years with very good results in the last 2 years. I have shifted mainly from a discretionary to a more quantitative trader. I used my skills in machine learning to generate reliable and profitable trading strategies.