Advanced Feature Engineering Techniques for Fraud Analytics

Abdelrahim Al Aqqad

Chapter Chapter 8 in Fraud Analytics in Action, 2026, pp 173-200 from Springer

Abstract: Abstract This chapter explores advanced feature engineering techniques tailored to fraud detection, with a particular emphasis on the role of temporal analysis in uncovering irregular transactional patterns. The chapter begins by introducing featurization as a systematic process for transforming raw transactional data into structured, high-value inputs for machine learning models. It then presents the construction of RFM (recency, frequency, and monetary) features, which collectively capture critical dimensions of customer behavior and serve as robust indicators of potential fraud. Within time-based feature engineering, the chapter introduces the Von Mises distribution as a method for modeling the cyclical nature of transaction timestamps. Through a practical example using circular statistics and polar visualizations, the chapter demonstrates how confidence interval-based indicators can be used to flag transactions occurring at atypical hours. The chapter further examines recency features, which quantify the time elapsed between similar events using exponential decay functions, frequency features, which track the rate of specific transactional activities across accounts, and monetary features, which identify anomalies in spending amounts and payment methods. Each feature type is illustrated through real-world scenarios and supported by Python-based implementations. The chapter concludes by highlighting the importance of combining these features with complementary data elements such as geolocation and user behavior analytics to build comprehensive and effective fraud detection systems.

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_8

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

DOI: 10.1007/978-3-032-16023-2_8

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 ().