Chapter 7. Fraud and Anomaly Detection

Outlier detection is used to identify exceptions, rare events, or other anomalous situations. Such anomalies may be hard-to-find needles in a haystack, but their consequences may nonetheless be quite dramatic, for instance, credit card fraud detection, identifying network intrusion, faults in a manufacturing processes, clinical trials, voting activities, and criminal activities in e-commerce. Therefore, discovered anomalies represent high value when they are found or high costs if they are not found. Applying machine learning to outlier detection problems brings new insight and better detection of outlier events. Machine learning can take into account many disparate sources of data and find correlations that are too obscure for human analysis to identify.

Take the example of e-commerce fraud detection. With machine learning algorithm in place, the purchaser's online behavior, that is, website browsing history, becomes a part of the fraud...