prikaz prve stranice dokumenta Detekcija prijevara u osiguranju motornih vozila
  Download
PDF 1.85 MB
professional thesis
Detekcija prijevara u osiguranju motornih vozila
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. urn:nbn:hr:168:929741
Hajdarović, Dijana
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Hajdarović, D. (2023). Detekcija prijevara u osiguranju motornih vozila (Professional thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:929741

Hajdarović, Dijana. "Detekcija prijevara u osiguranju motornih vozila." Professional thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:929741

Hajdarović, Dijana. "Detekcija prijevara u osiguranju motornih vozila." Professional thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2023. https://urn.nsk.hr/urn:nbn:hr:168:929741

Hajdarović, D. (2023). 'Detekcija prijevara u osiguranju motornih vozila', Professional thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 03 June 2024, https://urn.nsk.hr/urn:nbn:hr:168:929741

Hajdarović D. Detekcija prijevara u osiguranju motornih vozila [Professional thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2023 [cited 2024 June 03] Available at: https://urn.nsk.hr/urn:nbn:hr:168:929741

D. Hajdarović, "Detekcija prijevara u osiguranju motornih vozila", Professional thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2023. Available at: https://urn.nsk.hr/urn:nbn:hr:168:929741

Metadata
TitleDetekcija prijevara u osiguranju motornih vozila
Title (english)Motor insurance fraud detection
AuthorDijana Hajdarović
MentorZvonko Kostanjčar (mentor)
Committee memberStjepan Begušić (predsjednik povjerenstva)
Committee memberZvonko Kostanjčar (član povjerenstva)
Committee memberAzra Tafro (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2023, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
U radu se analiziraju metode za detekciju prijevarnih šteta na podacima o nastalim štetama na motornim vozilima u periodu od dvije godine u jednom osiguravajućem društvu u Republici Hrvatskoj. Cilj rada je ispitati dvije metode za nadzirano i jedne za nenadzirano učenje te na temelju dobivenih rezultata preložiti najbolju metodu i korake za poboljšanje dobivenih rezultata. Ispitivanje metoda napravljeno je na podacima koji se prikupljaju u procesu prijave i obrade odštetnih zahtjeva. Prije ispitivanja je napravljena analiza dostupnih varijabli i priprema za korištenje u prediktivnom modelu. Ispitivani su modeli logističke regresije i slučajnih šuma na 21 varijabli koja opisuje štete. Dodatno je implementirana k-means metoda kako bi se korištenjem metode lakta i metode siluete ispitalo koji bi bio optimalan broj klastera na korištenom uzorku podataka.
Abstract (english)
This paper analyzes methods for detecting fraudulent claims on data for motor claims in a period of two years in one insurance company in the Republic of Croatia. The aim of this paper is to test two methods for supervised and two methods for unsupervised learning and based on the obtained results to detect the best method and propose steps to improve it. Data used in this paper were collected during the first notice of loss and claim handling process. Before implementing predictive methods, data were analyzed and prepared for use. In this paper were tested logistic regression and random forest utilizing 21 variables as inputs for the models. Additionally, the k-means method was used to find an optimal number of clusters using the elbow and silhouette method.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:929741
Study programmeTitle: INSURTECH
Study programme type: university
Study level: postgraduate specialist
Academic / professional title: sveučilišni/a specijalist/specijalistica digitalnih inovacija i tehnologija u osiguranju (sveučilišni/a specijalist/specijalistica digitalnih inovacija i tehnologija u osiguranju)
Type of resourceText
File originBorn digital
Access conditionsOpen access
Terms of useLicence In copyright icon
Created on2024-05-03 11:09:13