Topic: Python for Data Science – Anomaly Detection II

Date/Time: Dec. 2, Thursday, 11:00 AM – 12:00 PM EST.

Abstract: Anomaly detection (also known as outlier detection), is the process of finding items or events in data sets that do not conform to the norm (expected behavior). Applications of anomaly detection include fraud detection in financial transactions, fault detection in manufacturing, intrusion detection in a computer network, monitoring sensor readings in an aircraft, spotting potential risk or medical problems in health data, etc.

In data science literature, there are three types of anomalies:

• Global
• Contextual
• Collective

Understanding these types can significantly affect the way of dealing with anomalies.

This session will focus on how to detect different types of "anomalies" in a time series data using Python.

Knowledge of time series analysis and basic Python (numpy, pandas, matplotlib, etc.) will be helpful for understanding the contents of this session.

** Google Colab will be used to do all the demos.

** A Zoom link will be emailed to all registered participants prior to the webinar.

Here is the registration link:

https://libcal.dartmouth.edu/calendar/itc/pyfds2021f2

Look forward to seeing you at the webinars.