(1) DATASET SELECTION

(2) DATA PREPROCESSING

- Scaling

- Feature Selection

- Filtering

(3) SAMPLING / BALANCING

- SMOTE / Upsample / Downsample

(4) MODEL TRAINING

Random Forest Model,

XG Boost

(5) MODEL EVALUATION

- Confusion Matrix

- Accuracy, Recall

- F1, ROC-AUC

FINAL RESULTS

First Level DFD

Preprocessed Data (D1)

Balanced Data (D2)

Trained Model (D3)