Isolation forest is an unsupervised learning algorithm for anomaly detection that works by isolating anomalies directly, rather than by first building a profile of what counts as normal and then flagging points that do not fit it. Because it does not need to construct a normal-behavior model, it can exploit sampling techniques unavailable to profile-based methods, producing a fast algorithm with low memory demand.
Sources
scikit-learn: scikit-learn: Novelty and Outlier Detection
scikit-learnIn Group: Outlier Detection Algorithms, Section 2.7.3.2 Isolation ForestQuote, In Group: Outlier Detection Algorithms, Section 2.7.3.2 Isolation Forest
One efficient way of performing outlier detection in high-dimensional datasets is to use random forests.
Reader Challenges (0)
No disputes yet. Spotted an error or a better source? Open the first one.
Sign in to dispute this or suggest a correction.