Introduction to Outlier Detection

4 hours of instruction

Detecting outlier data points are powerful machine learning techniques. This class will build upon foundational machine learning techniques to discover critical danger points in patterns. By the end of this course, students will use techniques like DBSCAN and SMOTE to identify anomalous data points.

OBJECTIVES

1. Define use cases for anomaly and outlier detection
2. Understand the concepts of DBSCAN and SMOTE models and how these models can be used for anomaly and outlier detection

PREREQUISITES

Introduction to Clustering in Python

SYLLABUS & TOPICS COVERED

1. Anomaly Basics
   • Anomaly detection basics and use cases
   • Definition of different types of outliers / anomalies
2. DBSCAN
   • Use DBSCAN as an anomaly detection technique
3. SMOTE
   • Role of SMOTE in anomaly detection

SOFTWARE REQUIREMENTS

You will have access to a Python-based JupyterHub environment for this course. No additional download or installation is required.