To evaluate the qualitative model, common classification metrics were calculated using the validation set.

The following confusion matrix values were obtained, followed by key metrics:

• True Positives (TP): Correctly predicted positives.
• False Positives (FP): Incorrectly predicted positives (actually negative).
• True Negatives (TN): Correctly predicted negatives.
• False Negatives (FN): Incorrectly predicted negatives (actually positive).

Based on these values, the following metrics were computed:

• Accuracy: 99.43%
• TNR (True Negative Rate): 99.66%
• Balanced Accuracy: 93.40%
• Recall (Sensitivity): 87.14%
• Precision: 82.75%
• F1 Score: 84.89%
• MCC (Matthews Correlation Coefficient): 0.85

For the quantitative model, the evaluation was based on regression metrics, including mean square error (MSE), mean absolute error (MAE), and Pearson's correlation coefficient.

The results are summarized as follows:

• Pearson's Coefficient: 0.62
• MAE (Mean Absolute Error): 0.40
• MSE (Mean Square Error): 0.37
• RMSE (Root Mean Square Error): 0.60

For a detailed analysis, view our full measurement report below: