Machine Learning in Python for Cryptocurrency Trading

Name: Machine Learning in Python for Cryptocurrency Trading
Rating: 4.1 (12 reviews)

Learn to predict cryptocurrency future prices using the power of Python Machine Learning (Artificial Intelligence)

Created byTauqeer Khurram

Last updated 5/2022

English

English [Auto],

What you'll learn

Learn to Predict Future Cryptocurrency Prices with ML Python Coding.
Learn to Build Machine Learning Models for Cryptocurrency Price Predictions.
Create a Web App that will Predict Cryptocurrency Future Prices.
Learn to Deploy Machine Learning Models for Cryptocurrency Price Prediction.

Course content

9 sections • 37 lectures • 7h 32m total length

Promo Video (Introduction)3:03
An overview of what is inside the course, and some of the awesome things that you will learn.

02 Setting up the Coding Environment - 120:13
This is the lecture, where I give introduction to the software tools,, most of which are open source and free. Then I show you how to create virtual environments for coding. Virtual environment isolates your code from the rest of the software on your machine.
02 Setting up the Coding Environment - 29:52
In this lecture, you will learn about the Python distribution Anaconda and code editors (or Integrated Development Environments) like "Jupyter" and "Visual Studio Code" used in the course.

01 Python Crash Course - Overview3:03
If you are beginner in Python coding, this is a Python crash course that will get you up and going for this course.
03 Python Comments6:53
This lecture has discussion about Python code comments.
03 Python Variables10:29
In this lecture, I discuss Python variables.
04 Python Functions and Methods7:24
This lecture contains the overview on Python functions and methods.
05 Data types in Python7:22
This lecture discusses about data types in Python like integers, floats , strings etc.
06 Pandas DataFrame3:10
This lecture contains the necessary information on Pandas DataFrame.
07 CSV Data Files Format4:02
This lecture has a brief introduction on csv data files.
08 Python Libraries10:30
This lecture has some information on Python libraries (aka modules, and packages).

01 Machine Learning - Introduction10:04
02 Machine Learning for Crypto Trading2:56
03 Machine Learning Algorithms 1013:26
04 Machine Learning Models 1012:22
Learn how machine learning models combine data and algorithms to produce trained code that recognizes patterns and predicts cryptocurrency prices.
05 ML Algorithms vs ML Models - The Difference4:57
Compare machine learning algorithms and models, clarifying data plus algorithms create models outputting what is learned. Show how algorithms use mathematics and pseudocode and are implemented in languages like Byton.
06 Regression vs Classification5:47
Identify supervised and unsupervised learning, distinguish classification and regression with discrete versus continuous outcomes, and apply regression algorithms to predict the future prices of cryptocurrencies.

01 Candlestick OHLC6:33
Explore candlestick OHLC concepts—open, high, low, close—bullish and bearish candles with bodies and shadows, and how these charts feed price data for algorithmic trading with machine learning.
02 Obtaining Crypto data Using yFinance23:22
Learn how to obtain crypto data with yfinance from Yahoo! Finance, downloading historical data for BTC USD, ETH USD, and LTC USD, including open, high, low, close, and volume.
03 Data Inspection and visualization31:21
04 Measuring Cryptocurrency Performance35:30
05 Calculating Returns from Historical Data21:50
05 Calculating Returns from Historical Data21:50
Calculate returns from historical cryptocurrency data by applying percent change and lag techniques, then resample to monthly BTC-USD data to analyze monthly returns.
06 Regularization or Normalization of Data10:40
Learn how to localize and normalize cryptocurrency data in Python, compare Bitcoin, Ethereum, and Litecoin, and see how normalization reveals the true top performer.
07 Covariance and Correlation13:55
Learn to compute covariance and correlation of cryptocurrency returns in Python for bitcoin, ethereum, and litecoin; interpret signs and visualize relationships with a heatmap.

01 Performance Evaluation (Risk-Return)16:04
Evaluate performance across Bitcoin, Litecoin, and Etherium by comparing risk and return with a normalized dataset, using annual mean and standard deviation to guide asset selection.
02 ETHUSD Data Download6:15
Selects Ethereum as the best crypto and downloads ETHUSD data from Yahoo Finance using yfinance, drops the adjusted close, and keeps open, high, low, close, and volume for machine learning.

01 Simple Linear Regression3:08
Learn how simple linear regression models the relationship between two variables, with input x and output y, visualize it via a scatterplot, make predictions, and deploy models online in Python.
02 Predicting Crypto Prices - Simple Linear Regression30:54
learn how to predict Ethereum prices with simple linear regression using close prices, build a 10-day projection, and evaluate with an 80-20 train-test split while plotting the regression results.
03 Support Vector Machine (SVM)16:02
04 Predicting Crypto Prices - SVM27:52
05 XGBoost1:42
06 Predicting Crypto Prices - XGBoost11:47

01 Residual Error5:47
Define residual error as difference between actual value and predicted value, with Y as actual and Y hat as prediction, using inputs X open, high, low, close prices and volume.
02 R Squred Error Intuition11:17
Explore how the R-squared statistic measures how well a regression model fits cryptocurrency price data by comparing predicted values to actual values and analyzing residual variance and outliers.
03 R Squared Error Implementation3:29

Requirements

Very little or no programming language experience required, you will learn everything you need to know
Knowledge of Markup languages such as HTM5 and CSS3 will help.

Description

It is a comprehensive course that shows how you can build a stylish web app with machine learning at the backend to predict the future price of any cryptocurrency. The main course has a mini crash course on Python for newbies and culminates into the theory and practice of Machine Learning and its predictive modeling application on cryptocurrencies.

At the end of this course, you will be able to develop a full-fledged web app that will take in data (available for free on the Internet). As you will provide the data to the web app, the web app having its predictive machine learning model at the backend will spit out the future prices of a cryptocurrency.

The course includes all the code for the web app, and with a tiny tuning in the code, you can adjust the web app to predict the prices of any cryptocurrency. And for any number of days in the future (recommended not to proceed more than 10-15 days for accuracy).

All the tools, software, and data used in the course can be downloaded for free and put to use instantly.

This course builds Machine Learning models from three popular algorithms. With Python code taking advantage of the predictive nature of machine learning, that can detect patterns in data that humans are not capable of doing. All the models go through evaluation for their accuracy before deployment.

I hope you will be able to build bigger, better, more efficient, and more effective models and web apps to predict cryptocurrency future prices with more accuracy.

Who this course is for:

Python Programmers, Data Scientist, Algorithmic Traders, AI Engineers, Computer Programmers, Cryptocurrency junkies and enthusiasts, Machine Learning Engineers who want to learn to predict future cryptocurrency prices.

Machine Learning in Python for Cryptocurrency Trading

What you'll learn

Explore related topics

Course content

Getting Started1 lecture • 3min

Coding Environments2 lectures • 30min

Python Crash Course8 lectures • 53min

04 Machine Learning6 lectures • 30min

05 Cryptocurrency Data Preprocessing & Analysis8 lectures • 2hr 45min

06 Performance Evaluation of Cryptocurrencies2 lectures • 22min

07 Predicting Crypto Prices with Machine Learning6 lectures • 1hr 31min

08 ML Model Evaluation3 lectures • 21min

09 ML Model Deployment1 lecture • 37min

Requirements

Description

Who this course is for: