Isolation Forestanomaly detectioniForestlinear time complexitysub-sampling
Figures from the paper
Abstract (AI)
Most existing model-based approaches to anomaly detection construct a profile of normal instances, then identify instances that do not conform to the normal profile as anomalies. This paper proposes a fundamentally different model-based method that explicitly isolates anomalies instead of profiles normal points. To our best knowledge, the concept of isolation has not been explored in current literature. The use of isolation enables the proposed method, iForest, to exploit sub-sampling to an extent that is not feasible in existing methods, creating an algorithm which has a linear time complexity with a low constant and a low memory requirement. Our empirical evaluation shows that iForest performs favourably to ORCA, a near-linear time complexity distance-based method, LOF and random forests in terms of AUC and processing time, and especially in large data sets. iForest also works well in high dimensional problems which have a large number of irrelevant attributes, and in situations where training set does not contain any anomalies.
Key Findings
1
Empirical evaluation shows iForest performs favorably to ORCA, LOF, and random forests in AUC and processing time, particularly on large datasets.
2
Introduces isolation (iForest) as a novel model-based anomaly detection method that isolates anomalies rather than profiling normal instances.
3
iForest handles high-dimensional data with many irrelevant attributes effectively.
4
iForest leverages subsampling extensively, yielding linear time complexity with a low constant and low memory requirement.
5
iForest remains effective even when the training set contains no anomalies.
Research Object
Isolation Forest (iForest) algorithm for anomaly detection
Research Subject
Isolation-based anomaly detection performance and computational properties (accuracy/AUC, processing time, scalability, memory use, robustness to high dimensionality and presence/absence of anomalies in training data)
Publication Details
Publication Date
2008-12-01
Journal
Publisher
ISSN
Cited by
7038
Access Type
Author Information
Download PDF
Subscribe to digest
Cited by13
Isolation-Based Anomaly Detection2012
A Unifying Review of Deep and Shallow Anomaly Detection2021
Anomaly detection in time series: a comprehensive evaluation2022
Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances2021
A Survey of Deep Learning Methods for Cyber Security2019
DeepAnT: A Deep Learning Approach for Unsupervised Anomaly Detection in Time Series2018
Practical Approach to Asynchronous Multivariate Time Series Anomaly Detection and Localization2021
A Survey on Explainable Anomaly Detection2023
Recent Advances in Anomaly Detection Methods Applied to Aviation2019
FraudGNN-RL: A Graph Neural Network With Reinforcement Learning for Adaptive Financial Fraud Detection2025
Automated Monte Carlo-based quantification and updating of geological uncertainty with borehole data (AutoBEL v1.0)2020
Time Series Anomaly Detection Leveraging MSE Feedback with AutoEncoder and RNN2024
Predictive Analytics in Anti-Corruption and Public Financial Oversight: Advances and Opportunities2022