What do the KNN classification evaluation metrics suggest about the model? Tx!

Confusion Matrix Actual Predicted - 0 - 1 0 16 15 22 31 Error Report Class Cases # Errors - % Error M 0 31 15 48.38709677 53 22 41.50943396 Overall 84 37 44.04761905 Metrics Metric Value Accuracy (#correct) 47 Accuracy (correct) 55.95238095 Specificity 0.516129032 Sensitivity (Recall 0.58490566 Precision 0.673913043 F1 score 0.626262626 Success Class Success Probability 0.5. These test classification confusion matrix, error report, and other metrics are the result of a technique used to classify customers with low risk who apply for loans at a Credit Union. Low risk is class 1, and high risk is class 0. What do the KNN classification evaluation metrics suggest about the model? Select one: O a. All the given answers are true. b. The model is better at classifying customers with high risk O c. The model has low efficacy (effectiveness); in fact, it is just somewhat better than random prediction. O d. The model is better at classifying customers with high risk, and has low efficacy (effectiveness). In fact, it is just somewhat better than random prediction. O e. The model has a near-perfect Precision metric