Machine Learning

A typical organization loses an estimated 5% of its yearly revenue to fraud.

In this lab we're going to:

• use TPOT (AutoML) to automatically discover well-performing models.

• apply supervised learning algorithms to detect fraudulent behavior based upon past fraud.

• use unsupervised learning methods to discover new types of fraud activities.

Fraudulent transactions are rare compared to the norm. As such, learn to properly classify imbalanced datasets.

The following video introduces the main Topics covered in the Lab.

To watch the videos please copy and paste the website URL into your host Chrome browser.

Lab Overview