An efficient banking fraud detection system using grasshopper optimization algorithm in comparison with integrated component analysis

The aim of the work is to employ Novel Classification techniques for detection of bank frauds to increase accuracy using Grasshopper Optimization algorithm (an innovative GOA) and Integrated Component Analysis (ICA). Materials and Methods: The sample size employed for detection of bank frauds system...

Full description

Saved in:
Bibliographic Details
Main Authors: Preethi, S., Sabitha, R.
Format: Conference Proceeding
Language:English
Subjects:
Accuracy
Algorithms
Classification
Optimization
Optimization algorithms
Recall
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The aim of the work is to employ Novel Classification techniques for detection of bank frauds to increase accuracy using Grasshopper Optimization algorithm (an innovative GOA) and Integrated Component Analysis (ICA). Materials and Methods: The sample size employed for detection of bank frauds system prediction was 3500 (Group 1=1750 and Group 2 =1750). Novel Classification of enhanced detection of bank frauds is performed by innovative GOA and ICA techniques. Results: The accuracy rate of an innovative GOA is 95.01% whereas results of ICA accuracy rate are 87.59%. The precision rate is 94.93% for an innovative GOA whereas results of ICA precision rate are 88.46%. The recall rate is 93.71% for an innovative GOA whereas results of ICA recall rate is 89.24%. The specificity rate is 95.143% for an innovative GOA whereas results of ICA specificity is 89.18%. There is a significant difference in Accuracy rate (P=0.0401). Conclusion: an innovative GOA Classifier predicts the better Novel Classification in finding the accuracy rate for detection of bank frauds systems when compared to ICA.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0176990