Classification-Based Machine Learning for Finance
5.0 (1 rating)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
79 students enrolled
Wishlisted Wishlist

Please confirm that you want to add Classification-Based Machine Learning for Finance to your Wishlist.

Add to Wishlist

Classification-Based Machine Learning for Finance

Hands on guide on using classification based Machine Learning techniques with application in finance and investment
New
5.0 (1 rating)
Instead of using a simple lifetime average, Udemy calculates a course's star rating by considering a number of different factors such as the number of ratings, the age of ratings, and the likelihood of fraudulent ratings.
79 students enrolled
Created by Anthony NG
Last updated 8/2017
English
Current price: $10 Original price: $200 Discount: 95% off
5 hours left at this price!
30-Day Money-Back Guarantee
Includes:
  • 4.5 hours on-demand video
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
What Will I Learn?
  • Understand and implement logistic regression, linear discriminant analysis, quadratic discriminant analysis, Stochastic Gradient Descent classifier, Nearest Neighbors, Gaussian Naive Bayes and many more in Python for investment.
  • Design investment strategies following professional Quant work flow
  • Understanding and implement machine learning techniques utilizing Python scikit-learn library.
  • Gain a deeper appreciation of challenges of modelling financial time series
  • Understand the different categories of machine learning
  • Understand the limitations of various machine learning techniques
  • Develop a deep intuition of machine learning project and avoid making costly mistakes
View Curriculum
Requirements
  • Good understanding of Python data science stack.
  • Deep appreciation of finance, algorithmic trading, and hedge fund investment strategies
Description

Finally, a comprehensive hands-on machine learning course with specific focus on classification based models for the investment community and passionate investors. 

In the past few years, there has been a massive adoption and growth in the use of data science, artificial intelligence and machine learning to find alpha. However, information on and application of machine learning to investment are scarce. This course has been designed to address that. It is meant to spark your creative juices and get you started in this space.

In this course, we are first going to provide some background information to machine learning. To ease you into the machine learning lingo, we start will something that most people are familiar with – Logistic Regression. The assumptions of financial time series as well as the stylized facts are introduced and explained at length due to its importance. The assumptions of linear regression are also highlighted to demonstrate the challenges and danger of blindly applying machine learning to investment without proper care and considerations to the nuances of financial time series.

After covering the basics of classification based machine learning using logistic regression, we then move on to more advanced topics covering other classification machine learning algorithms such as Linear Discriminant Analysis, Quadratic Discriminant Analysis, Stochastic Gradient Descent classifier, Nearest Neighbors, Gaussian Naive Bayes and many more. We follow the foundations that we started in the first regression based machine learning course covering cross-validation, model validation, back test, professional Quant work flow, and much more.

This course not only covers machine learning techniques, it also covers in depth the rationale of investing strategy development. 

This course is the second of the Machine Learning for Finance and Algorithmic Trading & Investing Series. The courses in the series includes:

  • Regression-Based Machine Learning for Algorithmic Trading
  • Classification-Based Machine Learning for Algorithmic Trading 
  • Ensemble Machine Learning for Algorithmic Trading 
  • Unsupervised Machine Learning: Hidden Markov for Algorithmic Trading 
  • Clustering and PCA for Investing

If you are looking for a course on applying machine learning to investing, the Machine Learning for Finance and Algorithmic Trading & Investing Series is for you. With over 30 machine learning techniques test cases, which included popular techniques such as Lasso regression, Ridge regression, SVM, XGBoost, random forest, Hidden Markov Model, common clustering techniques and many more, to get you started with applying Machine Learning to investing quickly. 

Who is the target audience?
  • Investment professionals who is interested to learn to apply classification-based machine learning techniques to investing strategies
  • Investment professionals and students who would are sourcing innovative investment ideas
  • Anyone looking for ideas and gentle introduction to how artificial intelligence (AI) can be applied to investing
Compare to Other Machine Learning Courses
Curriculum For This Course
27 Lectures
04:17:16
+
Introduction To Machine Learning For Algorithmic Trading
5 Lectures 42:43
Brief Introduction to Machine Learning
05:38

Machine Learning Project Check List Part 1
12:43

Machine Learning Project Check List Part 2
10:00


Financial Time Series Characteristics
05:58
+
Logistic Regression
2 Lectures 25:11
Understanding Logistic Regression
11:16

Logistic Regression and Scikit Learn
13:55
+
Classification - A Walk Through Tutorial
5 Lectures 01:03:40
Understanding Classification ML and Data Exploration
09:12

Building a Simple Classifier and Performing Cross Validation
15:23

Confusion Matrix
15:51

Precision/Recall Tradeoff
14:25

The Receiver Operating Characteristics (ROC) Curve
08:49
+
Default Prediction
2 Lectures 22:37
Template
10:27

Default prediction with LDA, KNN and Random Forest
12:10
+
Predicting Next Day's Returns
5 Lectures 50:01
Background to Returns Prediction
09:14

Predicting Next Day's Returns Using Logistic Regression
10:01

Predicting Next Day's Returns Using LDA and QDA
07:33

Price Prediction Using Real Market Data from Quantopian
07:10

Back Test and Tear Sheet
16:03
+
Ideas
1 Lecture 18:29
Ideas
18:29
+
Global Stock Selection Strategy
2 Lectures 15:45
Introduction to Alpha Factors
08:32

Global Stock Selection Strategy
07:13
+
Bonus Section
1 Lecture 01:46
Bonus Lecture
01:46
About the Instructor
Anthony NG
4.3 Average rating
157 Reviews
2,229 Students
5 Courses
Algorithmic Trading Workshop Researcher and Conductor

Anthony Ng has spent the last seven years as a Senior Lecturer teaching algorithmic trading, financial data analysis, banking, finance, investment and portfolio management. He assists Quantopian, a Boston-based Hedge Fund, to conduct Algorithmic Trading Workshops in Singapore and has presented in the recent QuantCon Singapore 2016. You can find his Algorithmic Trading tutorials on his YouTube channel. Just click the YouTube icon to visit his channel.

Passionate with finance, data science and python, Anthony enjoyed researching, teaching and sharing on these topics. Anthony studied Masters of Science in Financial Engineering at NUS Singapore.