TY - JOUR
T1 - Feature selection using evolutionary algorithms
T2 - a data-constrained environment case study to predict tax defaulters
AU - Sharma, Chethan
AU - Agnihotri, Manish
AU - Rathod, Aditya
AU - Shenoy, K. B.Ajitha
N1 - Publisher Copyright:
Copyright © 2022 Inderscience Enterprises Ltd.
PY - 2022
Y1 - 2022
N2 - In this paper, a novel method is introduced to predict tax defaulters from the given data using an ensemble of feature reduction in the first step and feeding those features to a proposed neural network. The feature reduction step includes genetic algorithm (GA), particle swarm optimisation (PSO) and ant colony optimisation (ACO) in the performance analysis to determine the best approach. The second stage deals with experiments on the architecture of a neural network for appropriate predictions. The results indicate improvement in tax defaulter prediction on using the feature subset selected by PSO. This research work has also successfully demonstrated the positive influence on the usage of linear discriminant analysis (LDA) to perform dimensionality reduction of the unselected features to preserve the underlying patterns. The best results have been achieved using PSO for feature reduction with an accuracy of 79.2% which is a 5.4% improvement compared to the existing works.
AB - In this paper, a novel method is introduced to predict tax defaulters from the given data using an ensemble of feature reduction in the first step and feeding those features to a proposed neural network. The feature reduction step includes genetic algorithm (GA), particle swarm optimisation (PSO) and ant colony optimisation (ACO) in the performance analysis to determine the best approach. The second stage deals with experiments on the architecture of a neural network for appropriate predictions. The results indicate improvement in tax defaulter prediction on using the feature subset selected by PSO. This research work has also successfully demonstrated the positive influence on the usage of linear discriminant analysis (LDA) to perform dimensionality reduction of the unselected features to preserve the underlying patterns. The best results have been achieved using PSO for feature reduction with an accuracy of 79.2% which is a 5.4% improvement compared to the existing works.
UR - http://www.scopus.com/inward/record.url?scp=85137086841&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137086841&partnerID=8YFLogxK
U2 - 10.1504/IJCC.2022.10049540
DO - 10.1504/IJCC.2022.10049540
M3 - Article
AN - SCOPUS:85137086841
SN - 2043-9989
VL - 11
SP - 345
EP - 355
JO - International Journal of Cloud Computing
JF - International Journal of Cloud Computing
IS - 4
ER -