search query: @keyword profiling / total: 7
reference: 2 / 7
« previous | next »
Author:Mansikkamäki, Ilkka
Title:Histogram based signatures for detecting warranty fraud
Histogrammeihin perustuvat allekirjoitukset takuupetosten havaitsemisessa
Publication type:Master's thesis
Publication year:2012
Pages:iv + 65      Language:   eng
Department/School:Matematiikan ja systeemianalyysin laitos
Main subject:Sovellettu matematiikka   (Mat-2)
Supervisor:Salo, Ahti
Instructor:Pere, Terhi
Electronic version URL: http://urn.fi/URN:NBN:fi:aalto-201211243391
OEVS:
Electronic archive copy is available via Aalto Thesis Database.
Instructions

Reading digital theses in the closed network of the Aalto University Harald Herlin Learning Centre

In the closed network of Learning Centre you can read digital and digitized theses not available in the open network.

The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/

You can read theses on the Learning Centre customer computers, which are available on all floors.

Logging on to the customer computers

  • Aalto University staff members log on to the customer computer using the Aalto username and password.
  • Other customers log on using a shared username and password.

Opening a thesis

  • On the desktop of the customer computers, you will find an icon titled:

    Aalto Thesis Database

  • Click on the icon to search for and open the thesis you are looking for from Aaltodoc database. You can find the thesis file by clicking the link on the OEV or OEVS field.

Reading the thesis

  • You can either print the thesis or read it on the customer computer screen.
  • You cannot save the thesis file on a flash drive or email it.
  • You cannot copy text or images from the file.
  • You cannot edit the file.

Printing the thesis

  • You can print the thesis for your personal study or research use.
  • Aalto University students and staff members may print black-and-white prints on the PrintingPoint devices when using the computer with personal Aalto username and password. Color printing is possible using the printer u90203-psc3, which is located near the customer service. Color printing is subject to a charge to Aalto University students and staff members.
  • Other customers can use the printer u90203-psc3. All printing is subject to a charge to non-University members.
Location:P1 Ark Aalto  213   | Archive
Keywords:warranty
fraud
histogram
profiling
signatures
clustering
behavior model
change detection
petoksen havaitseminen
histogrammi
profilointi
klusterointi
käyttäytymismalli
muutoksen havaitseminen
Abstract (eng): Companies in all industries lose billions of dollars due to fraud every year.
Fraud occurs in various ways, one being warranty fraud by repairing partners who invent their repair data.
The company that has outsourced its repair activities must have proper tools for detecting fraud.
However, it is often impossible to determine single repair data points as fraud, making it profitable for the company to determine the reliability of the repair vendor by investigating the overall performance.
This thesis focuses on estimating the reliability of the vendor by comparing the performance of each vendor against others.

This thesis introduces a histogram based profiling method that can be used for vendor comparison as a profile over a period of time or by updating the profile constantly and recording the changes in performance.
Profiles, called histogram signatures, are applied to clustering and local outlier methods.
Histogram signatures are also compared to identify the changes in the profiles of each vendort's peers.
Histograms are compared with Jensen-Shannon divergence difference.

The presented histogram method is tested with real repair data from an electronics company.
Fraudulent repair data is simulated to represent different fraud types.
The results show that single and momentary changes in the profile are not detected but the method is able to detect well big changes in repairing activity.
Abstract (fin): Yritykset menettävät petoksen takia miljardeja dollareja vuosittain.
Petosta ilmenee monin tavoin, kuten esimerkiksi huoltopartnerien tekaistulla takuunalaisella korjausdatalla.
Huoltotoimintansa ulkoistaneella yrityksellä pitääkin olla kattava tietojärjestelmä petoksen havaitsemiseksi.
Yksittäisiä huoltotapahtumia harvoin voidaan varmuudella arvioida petokseksi, joten yrityksen on kannattavaa tarkastella partnerin toiminnan luotettavuutta kokonaisuudessaan.
Tässä työssä määritellään partnerien epäilyttävyyttä vertaamalla kunkin huoltopartnerin toimintaa toisiin partnereihin.

Työssä esitellään histogrammeihin perustuva profilointimenetelmä, jolla huoltopartnerien toimintaa voidaan verrata sekä pitkän aikavälin että päivitettävänä, toiminnan muuttumista tarkkailevana profiilina.
Histogrammimenetelmää sovelletaan klusterointi- ja paikallisten poikkeamien havaitsemismenetelmiin sekä tutkitaan profiilin muutoksia lähimpiin naapureihin verrattuna.
Histogrammien vertailuun käytetään Jensen-Shannonin divergenssimittaa.

Esiteltyä histogrammimenetelmää testataan elektroniikkayrityksen huoltodatalla, johon generoidaan erilaisia poikkeuksellista huoltotoimintaa mallintavia datapisteitä.
Tuloksista käy ilmi, että menetelmä havaitsee heikosti yksittäisiä poikkeamia mutta hyvin suuria muutoksia huoltopartnereiden toiminnassa.
ED:2012-10-17
INSSI record number: 45361
+ add basket
« previous | next »
INSSI