Learners pursuing the MicroMasters programme are strongly recommended to complete PA1.1x Introduction to Predictive Analytics, PA1.2x Evaluation of Predictive Modelling and PA1.3x Statistical Predictive Modelling on the verified track prior to undertaking this course.
About this course
This course will give you an overview of various machine learning-based approaches for predictive modelling, including tree-based techniques, support vector machines, and neural networks.
Starting with a range of decision trees, including CART and C4.5, for classification and regression, you will be introduced to the concepts of information gain and other variable analysis measures, as well as the structure of decision trees.
You will also learn various sampling techniques such as bagging and boosting, which improve robustness and overall predictive power, as well as random forests. The differences will be illustrated in a small case study.
The course also covers support vector machines by introducing you to the concept of optimising the separation between classes. You will then dive into support vector regression.
Finally, you will look at neural networks; their topology, the concepts of weights, biases, and kernels, and optimisation techniques. These provide a good basis for future deep learning efforts.
Various trade-offs in terms of understandability and predictive power are covered against the backdrop of the various training issues and solutions that make neural networks such a prevalent, but often challenging, technique.
In the final week of the course, you will focus on an in-depth analysis and comparison of the techniques in the context of various case studies.
What you'll learn
- Learn how to apply machine learning-based predictive models
- Understand theory on tree-based models, support vector machines and neural networks
- Implement the theoretic models in machine learning-based software packages
- Compare and discuss machine learning-based models for different business applications
Week 2: Random forests and support vector machines
Week 3: Support vector machines
Week 4: Neural networks
Week 5: Neural network estimation and pitfalls
Week 6: Model comparison
Pursue a Verified Certificate to highlight the knowledge and skills you gain $300.00
Official and Verified
Receive an instructor-signed certificate with the institution's logo to verify your achievement and increase your job prospects
Add the certificate to your CV or resume, or post it directly on LinkedIn
Give yourself an additional incentive to complete the course
Support our Mission
EdX, a non-profit, relies on verified certificates to help fund free education for everyone globally
Frequently asked questions
This course foregrounds self-directed and active ways of learning: reading, coding in Python, knowledge check quizzes, and peer discussion. In addition, the course features videos that demonstrate relevant predictive analysis techniques and concepts.
What software will I be required to use?
All coding activities on this course will be hosted on Vocareum. You will be able to access this free software directly within the edX platform. There is no requirement to purchase further software in order to complete this course.
What do I need to complete the course?
For successful completion of this course, you will need access to a computer or mobile device and a reliable internet connection.
Who can take this course?
Unfortunately, learners from one or more of the following countries or regions will not be able to register for this course: Iran, Cuba and the Crimea region of Ukraine. While edX has sought licenses from the U.S. Office of Foreign Assets Control (OFAC) to offer our courses to learners in these countries and regions, the licenses we have received are not broad enough to allow us to offer this course in all locations. EdX truly regrets that U.S. sanctions prevent us from offering all of our courses to everyone, no matter where they live.