Naslov
Self-organizing maps for fraud profiling in leasing

Autori
Pejić Bach, Mirjana ; Vlahović, Nikola ; Pivar, Jasmina

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 41st International Convention on Information and Communication Technology, Electronics and Microelectronics MIPRO 2018 / Skala, Karolj - Opatija : Hrvatska udruga za informacijsku i komunikacijsku tehnologiju, elektroniku i mikroelektroniku - MIPRO, 2018, 1203-1208

ISBN
978-953-233-095-3

Skup
41st International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO 2018)

Mjesto i datum
Opatija, Hrvatska, 21.05.2018. - 25.05.2018

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Companies, Banking, Insurance, Self-organizing feature maps, Clustering algorithms

Sažetak
Fraud is intended and planned activity aimed at achieving material or immaterial gains against interests of an organization or a person. It often occurs in financial industries, such as banking, insurance, and leasing. The goal of this paper is to present a novel approach to profiling fraudulent behavior in leasing companies, using self-organizing maps. Dataset of one leasing company that consists of both fraudulent and non-fraudulent transactions has been analyzed. Cluster analysis has been applied using the self-organizing maps algorithm, with the support of Viscovery SOMine software. Five clusters were identified, that have a different structure according to an industry of the client, previous experience with a client, type of a leasing object, and status of a leasing object (new or used). The clusters were compared using chi-square test according to proportion of fraudulent and non-fraudulent transactions, resulting in profiles of clients and leasing objects that are more prone to fraudulent behavior.

Izvorni jezik
Engleski

Znanstvena područja
Ekonomija, Informacijske i komunikacijske znanosti

POVEZANOST RADA