Unsupervised Learning Techniques

Abdelrahim Al Aqqad

Chapter Chapter 11 in Fraud Analytics in Action, 2026, pp 241-270 from Springer

Abstract: Abstract This chapter examines unsupervised learning (USL) techniques as tools for detecting fraud in the absence of labeled data. Beginning with a conceptual distinction between supervised and unsupervised approaches, the chapter establishes why USL is particularly suited to fraud detection, where labeled examples of fraudulent activity are scarce or unavailable. Anomaly detection methods—including Isolation Forest, one-class support vector machines, and the local outlier factor—are presented for their capacity to isolate irregular transactions without prior knowledge of fraud characteristics. Dimensionality reduction techniques such as principal component analysis, autoencoders, and t-SNE are explored for their ability to compress high-dimensional data and surface latent fraud signals. Market basket analysis is reframed as a fraud detection instrument, demonstrating how Apriori and Eclat algorithms expose suspicious co-occurrence patterns within transactional data. Clustering algorithms—including K-Means, DBSCAN, and hierarchical clustering—are applied across banking, insurance, and social network fraud scenarios. Generative models, notably generative adversarial networks and variational autoencoders, are introduced for synthetic data augmentation and pattern learning in imbalanced datasets. The chapter concludes with Benford’s Law, illustrating how deviations in leading-digit distributions can indicate financial manipulation. Practical Python implementations and real-world case studies ground each technique in applied fraud analytics practice.

Date: 2026
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-032-16023-2_11

Ordering information: This item can be ordered from
http://www.springer.com/9783032160232

DOI: 10.1007/978-3-032-16023-2_11

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().