Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

Working of SVM variants and their working principles.

Linear SVM. Soft Margin SVM. Nonlinear SVM.

More »

Fig 1 Expand

Fig 2.

The RBF Curve.

Input space or non-linearly separable. RBF Kernel transformation. feature space linearly separable.

More »

Fig 2 Expand

Fig 3.

Conceptual view of random forest (RF).

RF Ensemble Learning Concept. Random created multiple trees related to the deco through bagging and random feature selection, then aggregated their predictions.

More »

Fig 3 Expand

Table 1.

Summary of recent literature on churn prediction.

More »

Table 1 Expand

Fig 4.

Research flow indicating hybrid strategy.

The First of Data Preparation consists of three steps. The Second phase of Model Development also consists of two steps.

More »

Fig 4 Expand

Table 2.

Dataset characteristics of the Bank Customer Churn Prediction dataset.

More »

Table 2 Expand

Fig 5.

Class Distribution of Churn Yes(1) and Non Churn(0).

More »

Fig 5 Expand

Fig 6.

Balance of Class Distribution using bar chart,box chart, violin plot and statistical analysis.

More »

Fig 6 Expand

Table 3.

Hyper-parameters and tuning considerations for the SVC-SDNN model.

More »

Table 3 Expand

Fig 7.

Dataset train-test distribution.

Overall bar chart of 20/80 distribution. Cross validation folds distribution. One cross-validation iteration. Class Distribution in Train-Test Split.

More »

Fig 7 Expand

Fig 8.

Comprehensive workflow of the proposed approach that highlights all the steps in this technique.

More »

Fig 8 Expand

Fig 9.

SVC-SDNN loss per fold.

ANN Component(of SVC-SDNN) Training and validation loss.

More »

Fig 9 Expand

Fig 10.

Normalized SVC-SDNN Confusion matrix.

More »

Fig 10 Expand

Table 5.

SVC-SDNN classification Report.

More »

Table 5 Expand

Table 4.

Comparative performance of machine learning models showing accuracy and AUC-ROC values.

More »

Table 4 Expand

Table 6.

RF-SDNN Classification Report.

More »

Table 6 Expand

Table 7.

SDNN Classification Report.

More »

Table 7 Expand

Fig 11.

RF-SDNN Normalized Confusion matrix.

More »

Fig 11 Expand

Fig 12.

SDNN Normalized Confusion matrix.

More »

Fig 12 Expand

Table 8.

SVM Classification Report.

More »

Table 8 Expand

Fig 13.

SVM Normalized Confusion Matrix.

More »

Fig 13 Expand

Table 9.

Performance comparison of machine learning models for churn prediction in banking dataset. Values represent mean ± 95% confidence interval across 5-fold cross-validation. RF-SDNN and SVC-SDNN represent hybrid models combining traditional classifiers with deep neural networks.

More »

Table 9 Expand

Fig 14.

Random Forest Confusion Matrix.

More »

Fig 14 Expand

Table 10.

Statistical significance testing results comparing traditional machine learning models with their hybrid SDNN counterparts across various performance metrics.

More »

Table 10 Expand

Table 11.

Performance comparison of base and hybrid models.

More »

Table 11 Expand