Outlier Detection (also known as Anomaly Detection) is an exciting yet challenging field, which aims to identify outlying objects that are deviant from the general data distribution. Outlier detection has been proven critical in many fields, such as credit card fraud analytics, network intrusion detection, and mechanical unit defect detection.

This repository collects:

1. Books & Academic Papers
2. Online Courses and Videos
3. Outlier Datasets
4. Open-source and Commercial Libraries/Toolkits
5. Key Conferences & Journals

More items will be added to the repository. Please feel free to suggest other key resources by opening an issue report, submitting a pull request, or dropping me an email @ ([email protected]). Enjoy reading!

BTW, you may find my [GitHub] and [outlier detection papers] useful, especially PyOD library and ADBench benchmark.

• 1. Books & Tutorials & Benchmarks
  • 1.1. Books
  • 1.2. Tutorials
  • 1.3. Benchmarks
• 2. Courses/Seminars/Videos
• 3. Toolbox & Datasets
  • 3.1. Multivariate data outlier detection
  • 3.2. Time series outlier detection
  • 3.3. Graph Outlier Detection
  • 3.4. Real-time Elasticsearch
  • 3.5. Datasets
• 4. Papers
  • 4.1. Overview & Survey Papers
  • 4.2. Key Algorithms
  • 4.3. Graph & Network Outlier Detection
  • 4.4. Time Series Outlier Detection
  • 4.5. Feature Selection in Outlier Detection
  • 4.6. High-dimensional & Subspace Outliers
  • 4.7. Outlier Ensembles
  • 4.8. Outlier Detection in Evolving Data
  • 4.9. Representation Learning in Outlier Detection
  • 4.10. Interpretability
  • 4.11. Outlier Detection with Neural Networks
  • 4.12. Active Anomaly Detection
  • 4.13. Interactive Outlier Detection
  • 4.14. Outlier Detection in Other fields
  • 4.15. Outlier Detection Applications
  • 4.16. Automated Outlier Detection
  • 4.17. Machine Learning Systems for Outlier Detection
  • 4.18. Fairness and Bias in Outlier Detection
  • 4.19. Isolation-based Methods
  • 4.20. Emerging and Interesting Topics
• 5. Key Conferences/Workshops/Journals
  • 5.1. Conferences & Workshops
  • 5.2. Journals

Outlier Analysis by Charu Aggarwal: Classical text book covering most of the outlier analysis techniques. A must-read for people in the field of outlier detection. [Preview.pdf]

Outlier Ensembles: An Introduction by Charu Aggarwal and Saket Sathe: Great intro book for ensemble learning in outlier analysis.

Data Mining: Concepts and Techniques (3rd) by Jiawei Han and Micheline Kamber and Jian Pei: Chapter 12 discusses outlier detection with many key points. [Google Search]

News: We just released a 36-page, the most comprehensive anomaly detection benchmark paper. The fully open-sourced ADBench compares 30 anomaly detection algorithms on 55 benchmark datasets.

Coursera Introduction to Anomaly Detection (by IBM): [See Video]

Get started with the Anomaly Detection API (by IBM): [See Website]

Practical Anomaly Detection by appliedAI Institute: [See Website], [See Video], [See GitHub]

Coursera Real-Time Cyber Threat Detection and Mitigation partly covers the topic: [See Video]

Coursera Machine Learning by Andrew Ng also partly covers the topic:

• Anomaly Detection vs. Supervised Learning
• Developing and Evaluating an Anomaly Detection System

Udemy Outlier Detection Algorithms in Data Mining and Data Science: [See Video]

Stanford Data Mining for Cyber Security also covers part of anomaly detection techniques: [See Video]

[Python] Python Outlier Detection (PyOD): PyOD is a comprehensive and scalable Python toolkit for detecting outlying objects in multivariate data. It contains more than 20 detection algorithms, including emerging deep learning models and outlier ensembles.

[Python, GPU] TOD: Tensor-based Outlier Detection (PyTOD): A general GPU-accelerated framework for outlier detection.

[Python] Python Streaming Anomaly Detection (PySAD): PySAD is a streaming anomaly detection framework in Python, which provides a complete set of tools for anomaly detection experiments. It currently contains more than 15 online anomaly detection algorithms and 2 different methods to integrate PyOD detectors to the streaming setting.

[Python] Scikit-learn Novelty and Outlier Detection. It supports some popular algorithms like LOF, Isolation Forest, and One-class SVM.

[Python] Scalable Unsupervised Outlier Detection (SUOD): SUOD (Scalable Unsupervised Outlier Detection) is an acceleration framework for large-scale unsupervised outlier detector training and prediction, on top of PyOD.

[Julia] OutlierDetection.jl: OutlierDetection.jl is a Julia toolkit for detecting outlying objects, also known as anomalies.

[Java] ELKI: Environment for Developing KDD-Applications Supported by Index-Structures: ELKI is an open source (AGPLv3) data mining software written in Java. The focus of ELKI is research in algorithms, with an emphasis on unsupervised methods in cluster analysis and outlier detection.

[Java] RapidMiner Anomaly Detection Extension: The Anomaly Detection Extension for RapidMiner comprises the most well know unsupervised anomaly detection algorithms, assigning individual anomaly scores to data rows of example sets. It allows you to find data, which is significantly different from the normal, without the need for the data being labeled.

[R] CRAN Task View: Anomaly Detection with R: This CRAN task view contains a list of packages that can be used for anomaly detection with R.

[R] outliers package: A collection of some tests commonly used for identifying outliers in R.

[Matlab] Anomaly Detection Toolbox - Beta: A collection of popular outlier detection algorithms in Matlab.

[Python] TODS: TODS is a full-stack automated machine learning system for outlier detection on multivariate time-series data.

[Python] skyline: Skyline is a near real time anomaly detection system.

[Python] banpei: Banpei is a Python package of the anomaly detection.

[Python] telemanom: A framework for using LSTMs to detect anomalies in multivariate time series data.

[Python] DeepADoTS: A benchmarking pipeline for anomaly detection on time series data for multiple state-of-the-art deep learning methods.

[Python] NAB: The Numenta Anomaly Benchmark: NAB is a novel benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications.

[Python] CueObserve: Anomaly detection on SQL data warehouses and databases.

[Python] Chaos Genius: ML powered analytics engine for outlier/anomaly detection and root cause analysis.

[R] CRAN Task View: Anomaly Detection with R: This CRAN task view contains a list of packages that can be used for anomaly detection with R.

[R] AnomalyDetection: AnomalyDetection is an open-source R package to detect anomalies which is robust, from a statistical standpoint, in the presence of seasonality and an underlying trend.

[R] anomalize: The 'anomalize' package enables a "tidy" workflow for detecting anomalies in data.

[Python] Python Graph Outlier Detection (PyGOD): PyGOD is a Python library for graph outlier detection (anomaly detection). It includes more than 10 latest graph-based detection algorithms

[Open Distro] Real Time Anomaly Detection in Open Distro for Elasticsearch by Amazon: A machine learning-based anomaly detection plugins for Open Distro for Elasticsearch. See Real Time Anomaly Detection in Open Distro for Elasticsearch.

[Python] datastream.io: An open-source framework for real-time anomaly detection using Python, Elasticsearch and Kibana.

ELKI Outlier Datasets: https://elki-project.github.io/datasets/outlier

Outlier Detection DataSets (ODDS): http://odds.cs.stonybrook.edu/#table1

Unsupervised Anomaly Detection Dataverse: https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/OPQMVF

Anomaly Detection Meta-Analysis Benchmarks: https://ir.library.oregonstate.edu/concern/datasets/47429f155

Skoltech Anomaly Benchmark (SKAB): https://github.com/waico/skab

Papers are sorted by the publication year.

All these algorithms are available in Python Outlier Detection (PyOD).

This section summarizes a list of systems for outlier detection, which may overlap with the section of tools and libraries.

Key data mining conference deadlines, historical acceptance rates, and more can be found data-mining-conferences.

ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD). Note: SIGKDD usually has an Outlier Detection Workshop (ODD), see ODD 2021.

ACM International Conference on Management of Data (SIGMOD)

The Web Conference (WWW)

IEEE International Conference on Data Mining (ICDM)

SIAM International Conference on Data Mining (SDM)

IEEE International Conference on Data Engineering (ICDE)

ACM InternationalConference on Information and Knowledge Management (CIKM)

ACM International Conference on Web Search and Data Mining (WSDM)

The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD)

The Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD)

ACM Transactions on Knowledge Discovery from Data (TKDD)

IEEE Transactions on Knowledge and Data Engineering (TKDE)

ACM SIGKDD Explorations Newsletter

Data Mining and Knowledge Discovery

Knowledge and Information Systems (KAIS)