Anomalies Detection in the Application Logs Using Kohonen SOM Machine Learning Algorithm

Izdanje: International Scientific Conference on Information Technology and Data Related Research

DOI: 10.15308/Sinteza-2020-275-282

Oblast: Advanced Computing

Stranice: 275-282

Apstrakt:
Internal fraud in the financial sector are difficult to detect since fraudulent transactions are indistinguishable from ordinary transactions, and standard checkpoints, in the form of transaction documentation and authorization, are skillfully avoided. Well-designed software has available and machine-readable application logs that can be analyzed to detect anomalies in application usage. This paper presents a data preparation technique using path analysis and Kohonen SOM clustering algorithm that can help better profile users of an application to reduce the number of cases that will be further investigated.
Ključne reči: internal fraud, Self-Organizing Mapping, Kohonen, path analysis, detection anomalies
Priložene datoteke:
  • 275-282 ( veličina: 624,27 KB, broj pregleda: 75 )

Preuzimanje citata:

BibTeX format
@article{article,
  author  = {V. Maksimović, M. Marjanović and A. Njeguš}, 
  title   = {Anomalies Detection in the Application Logs Using Kohonen SOM Machine Learning Algorithm},
  journal = {International Scientific Conference on Information Technology and Data Related Research},
  year    = 2020,
  pages   = {275-282},
  doi     = {10.15308/Sinteza-2020-275-282}
}
RefWorks Tagged format
RT Conference Proceedings
A1 Vladimir Maksimović
A1 Marina Marjanović
A1 Angelina Njeguš
T1 Anomalies Detection in the Application Logs Using Kohonen SOM Machine Learning Algorithm
AD Univerzitet Singidunum, Beograd, Beograd, Srbija
YR 2020
NO doi: 10.15308/Sinteza-2020-275-282
Unapred formatirani prikaz citata
V. Maksimović, M. Marjanović and A. Njeguš, Anomalies Detection in the Application Logs Using Kohonen SOM Machine Learning Algorithm, Univerzitet Singidunum, Beograd, 2020, doi:10.15308/Sinteza-2020-275-282