Anomaly Detection with Machine Learning and Graph Databases in Fraud Management
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2018, Vol 9, Issue 11
Abstract
In this paper, the task of fraud detection using the methods of data analysis and machine learning based on social and transaction graphs is considered. The algorithms for feature calculation, outlier detection and identifying specific sub-graph patterns are proposed. Software realization of the proposed algorithms is described and the results of experimental study of the algorithms on the sets of real and synthetic data are presented.
Authors and Affiliations
Shamil Magomedov, Sergei Pavelyev, Irina Ivanova, Alexey Dobrotvorsky, Marina Khrestina, Timur Yusubaliev
Keywords
Related Articles
- EP ID EP417583
- DOI 10.14569/IJACSA.2018.091104
- Views 98
- Downloads 0
Nonquadratic Lyapunov Functions for Nonlinear Takagi-Sugeno Discrete Time Uncertain Systems Analysis and Control
This paper deals with the analysis and design of the state feedback fuzzy controller for a class of discrete time Takagi -Sugeno (T-S) fuzzy uncertain systems. The adopted framework is based on the Lyapunov theory and us...
Using FDD for Small Project: An Empirical Case Study
Empirical analysis evaluates the proposed system via practical experience and reveals its pros and cons. Such type of evaluation is one of the widely used validation approach in software engineering. Conventional softwar...
An agent based approach for simulating complex systems with spatial dynamics application in the land use planning
In this research a new agent based approach for simulating complex systems with spatial dynamics is presented. We propose an architecture based on coupling between two systems: multi-agent systems and geographic informat...
Evaluating Damage Potential in Security Risk Scoring Models
A Continuous Monitoring System (CMS) model is presented, having new improved capabilities. The system is based on the actual real-time configuration of the system. Existing risk scoring models assume damage potential is...
Trajectory based Arabic Sign Language Recognition
Deaf and hearing impaired people use their hand as a tongue to convey their thoughts by performing descriptive gestures that form the sign language. A sign language recognition system is a system that translates these ge...