Practical Machine Learning: A New Look at Anomaly Detection

Table of contents

1. 1. Looking Toward the Future
2. 2. The Shape of Anomaly Detection
   1. Finding “Normal”
      1. If you enjoy math, read this description of a probabilistic model of “normal”…
   2. Human Insight Helps
   3. Finding Anomalies
      1. Once again, if you like math, this description of anomalies is for you…
      2. Take-Home Lesson: Key Steps in Anomaly Detection
   4. A Simple Approach: Threshold Models
3. 3. Using t-Digest for Threshold Automation
   1. The Philosophy Behind Setting the Threshold
   2. Using t-Digest for Accurate Calculation of Extreme Quantiles
   3. Issues with Simple Thresholds
4. 4. More Complex, Adaptive Models
   1. Windows and Clusters
   2. Matches with the Windowed Reconstruction: Normal Function
   3. Mismatches with the Windowed Reconstruction: Anomalous Function
   4. A Powerful But Simple Technique
   5. Looking Toward Modeling More Problematic Inputs
5. 5. Anomalies in Sporadic Events
   1. Counts Don’t Work Well
   2. Arrival Times Are the Key
      1. And Now with the Math…
   3. Event Rate in a Worked Example: Website Traffic Prediction
   4. Extreme Seasonality Effects
6. 6. No Phishing Allowed!
   1. The Phishing Attack
   2. The No-Phishing-Allowed Anomaly Detector
   3. How the Model Works
   4. Putting It All Together
7. 7. Anomaly Detection for the Future
8. A. Additional Resources
   1. GitHub
   2. Apache Mahout Open Source Project
   3. Additional Publications
9. About the Authors
10. Colophon
11. Copyright