Page 219 - AI Computer 10

Solution: Here, TP = 22, FP = 12, FN = 47, TN = 18

TP + TN
Accuracy = × 100
TP + FP + FN + TN
28 + 18
= × 100
22 + 18 + 12 + 47

= 40 × 100 = 40.40%
99
TP 22 22
Precision = = = = 0.6470 or 64.70%
TP + FP 22 + 12 34
TP 22 22
Recall = = = = 0.3188 or 3188%
TP + FN 22 + 47 69
2 × Precision × Recall 2 × 0.6470 × 0.3188 0.4125272
F1 Score = = = =.4271
Precision + Recall 0.6470 + 0.3188 0.9658

Example 2: A lot of times people face the problem of sudden downpour. People wash clothes and put them out
to dry, but due to unexpected rain, the clothes become wet again and their efforts get wasted. Thus, an AI model
has been created which predicts if there will be rain or not. The confusion matrix for the same is:

The Confusion Matrix Reality: 1 Reality: 0
Predicted: 1 5 0
Predicted: 0 45 50

Calculate Accuracy, Precision, Recall, and F1 Score for the above problem.
Solution: Here, TP = 5, FP = 0, FN = 45, TN = 50

TP + TN
Accuracy = × 100
TP + FP + FN + TN

5 + 50
= × 100
5 + 0 + 45 + 50

= 55 × 100 = 50%
100

TP 5 5
Precision = = = = 1 or 100%
TP + FP 5 + 0 5

TP 5 5
Recall = = = = 0.1 or 10%
TP + FN 5 + 45 50

F1 Score = 2 × Precision × Recall = 2 × 1 × 0.1 = 0.2 = 0.1818 or 18.18%
Precision + Recall 1 + 0.1 1.1
ETHICAL CONCERNS AROUND MODEL EVALUATION

As with all stages of AI project cycle, the evaluation stage also has ethical concerns related to it that need to be
resolved to create a well-balanced AI model. While evaluating an AI model, the following ethical concerns need
to be kept in mind:

85
85