Literature Review
Literature Review
1. 2021 An Enhanced IEEE Xplore K-Means filter, The dataset is a The Accuracy(in
Bank Genetic Bank dataset %) that was
Customers Algorithm and used for churn observed with
Churn Artificial Neural prediction different
Prediction Network challenges. algorithms are
Model ANN - 85.80
K-Means ANN -
99.90
GA K-Means
ANN - 100
2. 2022 Predicting 2022 5th ANN algorithm The dataset The accuracy in
Banking International contains predicting using
Customer Conference information the ANN
Churn based on about the algorithm - 86.4
on Artificial Computing customers in
Neural Network and banking sector,
Informatics and the
(ICCI) features that
indicates
whether the
customer left
the bank or
retained
customer.
6. 2020 Prediction of 2020 SVM and MLP Four segments Accuracy (in %)
Customer International networks of clients of the SVM - 99.6
Status in Joint chosen Polish MLP - 99.3
Corporate Conference bank have been Our results show
Banking Using on Neural considered in that the
Neural Networks this study. proposed
Networks (IJCNN) dynamic
behavioural
model related to
a few preceding
months could
predict the
customer
behaviour and
possible
churning
decisions in a
precise way
7. 2008 Churn 2008 Linear This algorithm Continuing
prediction with International Discriminant can deal with research should
Conference complicated aim at improving
Linear Boosting
on Machine binary the effectiveness
Discriminant Learning algorithm classification and
Boosting and problems, such generalization
algorithm Cybernetics as churn ability of
prediction with LD-Boosting.
an extremely
imbalanced
dataset.