On normalization and algorithm selection for unsupervised outlier detection

• Published in: Data mining and knowledge discovery Vol. 34; no. 2; pp. 309 - 354
• Main Authors: Kandanaarachchi, Sevvandi, Muñoz, Mario A., Hyndman, Rob J., Smith-Miles, Kate
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.03.2020; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Chemistry and Earth Sciences; Computer Science; Data analysis; Data Mining and Knowledge Discovery; Datasets; Information Storage and Retrieval; Outliers (statistics); Physics; Statistics for Engineering; Effect of normalization on outlier detection; Algorithm selection problem for outlier detection; Unsupervised outlier detection; Instance space analysis; Instance space analysis for outlier detection
• ISSN: 1384-5810; 1573-756X
• DOI: 10.1007/s10618-019-00661-z

This paper demonstrates that the performance of various outlier detection methods is sensitive to both the characteristics of the dataset, and the data normalization scheme employed. To understand these dependencies, we formally prove that normalization affects the nearest neighbor structure, and density of the dataset; hence, affecting which observations could be considered outliers. Then, we perform an instance space analysis of combinations of normalization and detection methods. Such analysis enables the visualization of the strengths and weaknesses of these combinations. Moreover, we gain insights into which method combination might obtain the best performance for a given dataset.