There and back again: Outlier detection between statistical reasoning and data mining algorithms
Open accessThe DOI matches its Crossref record; 29 of the 29 references it cites were found in a registry or an index.
Abstract
Outlier detection has been a topic in statistics for centuries. Over mainly the last two decades, there has been also an increasing interest in the database and data mining community to develop scalable methods for outlier detection. Initially based on statistical reasoning, however, these methods soon lost the direct probabilistic interpretability of the derived outlier scores. Here, we detail from a joint point of view of data mining and statistics the roots and the path of development of statistical outlier detection and of database‐related data mining methods for outlier detection. We discuss their inherent meaning, review approaches to again find a statistically meaningful interpretation of outlier scores, and sketch related current research topics. This article is categorized under:Algorithmic Development > Statistics Algorithmic Development > Scalable Statistical Methods Technologies > Machine Learning
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
Hanley, J. A., & McNeil, B. J. (1982) · Radiology · doi:10.1148/radiology.143.1.7063747 · Cited by 21,856 · cited 1×
“There is also a probabilistic interpretation:[78] If we choose a pair (o, i ) at random fromO × I , the ROCAUC value of a ranking is the probability that o and i are ranked in the correct order (i.”
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687
Scikit-learn: Machine Learning in Python
(2011) · Journal of Machine Learning Research · doi:10.5555/1953048.2078195 · Cited by 8,539
Ensemble methods in machine learning
Dietterich, T. G. (2000) · Lecture Notes in Computer Science · doi:10.1007/3-540-45014-9_1 · Cited by 8,408
Robust estimation of a location parameter
Huber, P. J. (1964) · The Annals of Mathematical Statistics · doi:10.1214/aoms/1177703732 · Cited by 7,228
LOF: identifying density-based local outliers
Breunig, M. M., Kriegel, H.-P., Ng, R. T., & Sander, J. (2000) · ACM SIGMOD Record · doi:10.1145/335191.335388 · Cited by 5,207
A Survey of Outlier Detection Methodologies
Hodge, V., & Austin, J. (2004) · Artificial Intelligence Review · doi:10.1007/s10462-004-4304-y · Cited by 3,596
Model-based analysis of oligonucleotide arrays: Expression index computation and outlier detection.
Li, C., & Wong, W. H. (2001) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.98.1.31 · Cited by 3,133
Hawkins, D. M. (1980) · doi:10.1007/978-94-015-3994-4 · Cited by 2,982 · cited 8×
“Let us, hence, designate, corresponding to Hawkins[82], those objects as “(true) outliers” that have been “generated by a different mechanism” than the remainder ormajor part of the data or than thewhatsoever defined reference set.”
Influentialhdbscan: Hierarchical density based clustering
McInnes, L., Healy, J., & Astels, S. (2017) · The Journal of Open Source Software · doi:10.21105/joss.00205 · Cited by 2,833
The Logic of Scientific Discovery
Popper, K. R., & Weiss, G. (1959) · Physics Today · doi:10.1063/1.3060577 · Cited by 2,717
Rokach, L. (2010) · Artificial Intelligence Review · doi:10.1007/s10462-009-9124-7 · Cited by 2,657
Measures of Diversity in Classifier Ensembles and Their Relationship with the Ensemble Accuracy
Kuncheva, L. I., & Whitaker, C. J. (2003) · Machine Learning · doi:10.1023/a:1022859003006 · Cited by 2,335 · cited 1×
“Ensemble learning, i.e., the combination of several learners or models to some meta-learner, meta-predictor, or meta-model, has a rich tradition and solid theory in the context of classification[54, 212, 30, 115, 168] and has also been transfered to the area of unsupervised learning.”
Pimentel, M. A. F., Clifton, D. A., Clifton, L., & Tarassenko, L. (2014) · Signal Processing · doi:10.1016/j.sigpro.2013.12.026 · Cited by 1,649 · cited 2×
“While recent comprehensive surveys like the works by Chandola et al.[37] and by Pimentel et al.[160] structure the literature according to specific techniques used (e.g., probabilistic, distance-based, clustering-based, information theoretic), here we rather see this as a continuum where the…”
Graph based anomaly detection and description: a survey
Akoglu, L., Tong, H., & Koutra, D. (2015) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0365-y · Cited by 1,504 · cited 2×
“[70] A recent survey on this area has been provided by Akoglu et al.[6] Also the context considered in a graph can be seen as a special case of locality for local outlier detection.”
Distance-based outliers: algorithms and applications
Knorr, E. M., Ng, R. T., & Tucakov, V. (2000) · The VLDB Journal The International Journal on Very Large Data Bases · doi:10.1007/s007780050006 · Cited by 1,195 · cited 2×
“A selection of prominent general examples could be a long list of references[102, 166, 94, 14, 22, 103, 15, 154, 62, 84, 73, 9, 143, 216, 28, 51, 198] and yet would be a close to arbitrary selection from the literature.”
Hierarchical Density Estimates for Data Clustering, Visualization, and Outlier Detection
Campello, R. J. G. B., Moulavi, D., Zimek, A., & Sander, J. (2015) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/2733381 · Cited by 915 · cited 2×
“GLOSH [33], for example, is provided by McInnes et al.[136], as part of the HDBSCAN scikit-learn contribution.”
Self-citationA survey on unsupervised outlier detection in high‐dimensional numerical data
Zimek, A., Schubert, E., & Kriegel, H. (2012) · Statistical Analysis and Data Mining The ASA Data Science Journal · doi:10.1002/sam.11161 · Cited by 864 · cited 5×
“• Fundamental challenges of high dimensional data for outlier detection have been discussed by Zimek et al.[228], and variousmethods dedicated to outlier detection in high dimensional data have been proposed.”
InfluentialSelf-citationAn Object-Oriented Framework for Robust Multivariate Analysis
Todorov, V., & Filzmoser, P. (2009) · Journal of Statistical Software · doi:10.18637/jss.v032.i03 · Cited by 420
A comprehensive survey of numeric and symbolic outlier mining techniques
Agyemang, M., Barker, K., & Alhajj, R. (2006) · Intelligent Data Analysis · doi:10.3233/ida-2006-10604 · Cited by 164 · cited 2×
“Agyemang et al.[5] are more interested in the data mining aspect of outlier detection as finding the rare, interesting”
Contextual anomaly detection framework for big sensor data
Hayes, M. A., & Capretz, M. A. (2015) · Journal of Big Data · doi:10.1186/s40537-014-0011-y · Cited by 149 · cited 1×
“[112, 108, 140, 141, 144, 51, 158, 97, 110, 46] • Another large subtopic is outlier detection in spatial data, trajectory data, or some other notion of separating context and indicator variables.[190, 126, 105, 199, 40, 193, 119, 124, 91, 118, 83, 121] The spatial neighborhood can be interpreted as a special case of l…”
Statistical selection of relevant subspace projections for outlier ranking
Muller, E., Schiffer, M., & Seidl, T. (2011) · 2011 IEEE 27th International Conference on Data Engineering · doi:10.1109/icde.2011.5767916 · Cited by 126
Explaining Outliers by Subspace Separability
Micenkova, B., Ng, R. T., Dang, X.-H., & Assent, I. (2013) · 2013 IEEE 13th International Conference on Data Mining · doi:10.1109/icdm.2013.132 · Cited by 104
Discovering outlying aspects in large datasets
Vinh, N. X., Chan, J., Romano, S., Bailey, J., Leckie, C., Ramamohanarao, K., & Pei, J. (2016) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0453-2 · Cited by 83 · cited 1×
“, “finding intensional knowledge”[101], “detection of outlying subspaces”[222], “outlier explanation”[137, 151], “interpreting outliers”[47, 46], “outlying aspect mining” (or “outlying aspect discovery”)[56, 213, 214], “outlying properties”[12, 11], or “characterizations”[13].”
Mining outlying aspects on numeric data
Duan, L., Tang, G., Pei, J., Bailey, J., Campbell, A., & Tang, C. (2015) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-014-0398-2 · Cited by 70
A decomposition of the outlier detection problem into a set of supervised learning problems
Paulheim, H., & Meusel, R. (2015) · Machine Learning · doi:10.1007/s10994-015-5507-y · Cited by 62 · cited 3×
“Also themethod of Paulheim andMeusel[151] models the data explicitly andmeasures the deviation of each point from its expected location (as predicted by some regression learning algorithm).”
Local Outlier Detection with Interpretation
Dang, X. H., Micenková, B., Assent, I., & Ng, R. T. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-40994-3_20 · Cited by 56
Outlying property detection with numerical attributes
Angiulli, F., Fassetti, F., Manco, G., & Palopoli, L. (2017) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-016-0458-x · Cited by 33 · cited 1×
“, “finding intensional knowledge”[101], “detection of outlying subspaces”[222], “outlier explanation”[137, 151], “interpreting outliers”[47, 46], “outlying aspect mining” (or “outlying aspect discovery”)[56, 213, 214], “outlying properties”[12, 11], or “characterizations”[13].”
(2004) · doi:10.1016/b978-012088469-8/50123-6 · Cited by 24
Cited by
Smart Anomaly Detection in Sensor Systems: A Multi-Perspective Review
Erhan, L., Ndubuaku, M., Di Mauro, M., Song, W., Chen, M., Fortino, G., Bagdasar, O., & Liotta, A. (2021) · Information Fusion · doi:10.1016/j.inffus.2020.10.001 · Cited by 378
A Review of Local Outlier Factor Algorithms for Outlier Detection in Big Data Streams
Alghushairy, O., Alsini, R., Soule, T., & Ma, X. (2020) · Big Data and Cognitive Computing · doi:10.3390/bdcc5010001 · Cited by 345
Barbado, A., Corcho, Ó., & Benjamins, R. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.116100 · Cited by 77
“One example is the work of [11], which covers different aspects related to outlier detection.”
BackgroundExplainable outlier detection: What, for Whom and Why?
Sejr, J. H., & Schneider-Kamp, A. (2021) · Machine Learning with Applications · doi:10.1016/j.mlwa.2021.100172 · Cited by 32
Random Subspace Mixture Models for Interpretable Anomaly Detection
Savkli, C., & Schwartz, C. (2021) · arXiv · doi:10.48550/arxiv.2108.06283 · Cited by 2
Metadata
- Authors
- Zimek, A., & Filzmoser, P.
- Venue
- WIREs Data Mining and Knowledge Discovery
- Publisher
- Wiley
- Published
- 2018-08-20
- Volume
- 8
- Issue
- 6
- ISSN
- 1942-4787 (ISSN-L)
- 1942-4795
- OpenAlex
- W2888297916
- Cited by
- 185
- References
- 29
- FWCI
- 9.62
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.