2021
DOI: 10.1155/2021/6618841
|View full text |Cite|
|
Sign up to set email alerts
|

Research on Credit Card Default Prediction Based on k-Means SMOTE and BP Neural Network

Abstract: Aiming at the problem that the credit card default data of a financial institution is unbalanced, which leads to unsatisfactory prediction results, this paper proposes a prediction model based on k-means SMOTE and BP neural network. In this model, k-means SMOTE algorithm is used to change the data distribution, and then the importance of data features is calculated by using random forest, and then it is substituted into the initial weights of BP neural network for prediction. The model effectively solves the p… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
5
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
8
1

Relationship

1
8

Authors

Journals

citations
Cited by 17 publications
(6 citation statements)
references
References 15 publications
0
5
0
1
Order By: Relevance
“…In this section, we aimed to evaluate the effectiveness of the proposed Ensemble Partition Sampling (EPS) method by comparing it to other imbalanced learning methods that have been previously proposed in the literature. To do this, we selected a number of representative methods from existing literature, including: OvA, SMOTE [26], k-means-SMOTE [27], and Bagging-RB [28]. The table 1 presents results of imbalanced learning methods using CART as a classifier on different datasets.…”
Section: A Comparison Of the Proposed Methods With Imbalanced Learnin...mentioning
confidence: 99%
“…In this section, we aimed to evaluate the effectiveness of the proposed Ensemble Partition Sampling (EPS) method by comparing it to other imbalanced learning methods that have been previously proposed in the literature. To do this, we selected a number of representative methods from existing literature, including: OvA, SMOTE [26], k-means-SMOTE [27], and Bagging-RB [28]. The table 1 presents results of imbalanced learning methods using CART as a classifier on different datasets.…”
Section: A Comparison Of the Proposed Methods With Imbalanced Learnin...mentioning
confidence: 99%
“…Recent developments in automated risk assessment models have surpassed traditional methods in almost all cases. Machine learning techniques like BP neural networks, KNN, and SVM are prevalent (Chen & Zhang, 2021). KNN outperformed the other two algorithms on two-class classification problems.…”
Section: Literature Reviewmentioning
confidence: 99%
“…KMeansSMOTE introduces structure to synthetic sample generation by combining KMeans clustering with SMOTE [19]. While it attempts to create samples in a more controlled manner, it is sensitive to the choice of the K parameter and may not perform well with non-convex clusters.…”
Section: Oversampling Techniquesmentioning
confidence: 99%