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