Use the built-in Amazon SageMaker Random Cut Forest algorithm for anomaly detection Amazon Web Services

Today, we are launching support for Random Cut Forest (RCF) as the latest built-in algorithm for Amazon SageMaker. RCF is an unsupervised learning algorithm for detecting anomalous data points or outliers within a dataset. This blog post introduces the anomaly detection problem, describes the Amazon SageMaker RCF algorithm, and demonstrates the use of the Amazon SageMaker RCF on an example real-world dataset. Suppose you have collected data on traffic volume over a period of time across multiple city blocks. Can you predict if a spike in traffic volume represents a collision or just the usual rush hour?