Download presentation
Presentation is loading. Please wait.
Published byGeoffrey Gyles Tate Modified over 9 years ago
1
By : Anas Assiri
2
Introduction fraud detection Immune system Artificial immune system (AIS) AISFD Clonal selection
3
Credit card transactions Number of Fraud cases Need for Fraud detection
4
deviation detection outlier analysis anomaly detection exception mining mining rare classes Fraud detection
5
Diversification Self- adaptation The fraud detection system with the increasing transactions should have more characteristics
6
The immune system is highly complicated detecting and eliminating infections similar problem: credit card fraud detection
7
Artificial immune system (AIS) Immunological computation is an area of biologically inspired computation.
8
Anomaly detection Patten recognition Data mining computer security adaptive control fault detection
9
AIS and other soft computing paradigms: ANN (artificial neural network) EA (evolutionary algorithms) FS (fuzzy system) PR (probabilistic reasoning).
10
Since only one financial transaction of a thousand is invalid Credit card fraud is rare event related to the total credit card records. AIS have the advantage of distinguish between : non-self cells ( fraud attempts ) self cells ( normal transactions ).
11
AISFD is a system based on AIS and case- based reasoning (CBR). Artificial Immune system is inspired from biological immune system. Tow main algorithms : Negative selection Clonal selection
13
Negative selection The purpose of negative selection is to provide self- tolerance to T-cells. It detects unknown antigens, without reacting with the self cells. Clonal selection The clonal selection principle describes the basic features of an immune response to an antigenic stimulus. It can make sure only the cells that can recognize the antigen can proliferate. Gene library evolution Gene library evolution learns knowledge of currently existing antigens.
15
library of past cases rather than being encoded in classical rules Each case typically contains : a description of the problem and a solution and or the outcome The knowledge and reasoning process used by an expert to solve the problem is not recorded, but is implicit in the solution
16
the problem is matched similar cases are retrieved suggest a solution reuse and test for success solution is revised problem and solution are retained as part of a new case. To solve a current problem:
17
Case library initialization (normal transactions and fraud transactions case) With supervised classification Antibody Gene (detectors.)library Initialization Random or genetic algorithms Negative selection of detectors Clonal selection of detectors
18
Fraud detection When a new transaction is submitted for fraud detection, the fraud detection function is activated. The affinity between the antibodies (detectors) in the gene library and the new antigens is calculated. If the affinity threshold set by the system is exceeded, the AISFD system sends out a fraud alert.
19
Diversification Online incremental learning Self-adaptation Distribution Fast response Multi-level classification
20
Thanks
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.