AI Application Development, Workshops, Full Day Hands-On Labs

AIF01 Hands-On Workshop: Build an Outlier Detector in a Day


8:00am - 5:00pm

Level: Introductory to Intermediate

Kevin Feasel


Catallaxy Services, LLC

Discovering outliers is a critical part of systems monitoring, financial auditing, and more. In this full-day workshop, we will gain an understanding of what constitutes an anomaly or an outlier, starting with a general concept of the terms and then moving into technical definitions. From there, we will build a general-purpose outlier detection API in Python, along with a test suite and demo client. We will extend this API to include a variety of use cases, including multivariate and time series outlier detection, learning about and applying state-of-the-art techniques along the way.

You will learn:

  • To understand what outliers and anomalies are
  • Discover the state of the art when it comes to outlier detection algorithms
  • How to build a web-based service to detect outliers in datasets

Attendee Requirements:

  • You must provide your own laptop 
  • Your machine must have a modern web browser
  • Python is required, preferably the Anaconda distribution but a base installation of Python will work fine.  Python 3.8 or later is recommended
  • A Git client is required.  We will interact with a variety of branches in a GitHub repository
  • Visual Studio Code is recommended, though other IDEs like PyCharm may also work
  • Postman is required for testing
  • Docker is not mandatory but may be helpful