P.S.

SENIOR SECONDARY SCHOOL

ARTIFICIAL INTELLIGENCE – 2021-22

EVALUATION – QUESTION AND ANSWERS

1. Define Evaluation
Evaluation is a process of understanding the reliability of any AI model, based on outputs by
feeding the test dataset into the model and comparing it with actual answers.

2. Which two parameters are considered for Evaluation of a model?

Prediction and Reality are the two parameters considered for Evaluation of a model. The
“Prediction” is the output which is given by the machine and the “Reality” is the real scenario,
when the prediction has been made.

3. What is True Positive?

 The predicted value matches the actual value.
 The actual value was positive and the model predicted a positive value

4. What is True Negative?

 The predicted value matches the actual value
 The actual value was negative and the model predicted a negative value

5. What is False Positive?

 The predicted value was falsely predicted.
 The actual value was negative but the model predicted a positive value
 Also known as the Type 1 error

6. What is False Negative?

 The predicted value was falsely predicted.
 The actual value was positive but the model predicted a negative value.
 Also known as the Type 2 error

7. What is meant by Overfitting of Data?

Overfitting is "the production of an analysis that corresponds too closely or exactly to a
particular set of data, and may therefore fail to fit additional data or predict future observations
reliably".

8. Can training data be used to evaluate an AI model. Justify your answer.

To evaluate an AI model the data that is used to build the model (training data) cannot be used.
Because AI Model remembers the whole training data set, it always predicts the correct label for
any point in the training dataset. Models that use the training dataset during testing will always
result in correct output. This may indicate that the model is Overfitting while the model may not
predict correct results for a new dataset.
9. What is Accuracy? Mention its formula
Accuracy is defined as the percentage of correct predictions out of all the observations. A
prediction is said to be correct if it matches reality. Here we have two conditions in which the
Prediction matches with the Reality, i.e., True Positive and True Negative. Therefore, Formula
for Accuracy is:

TP – TruePositive, TN – TrueNegative, FP – FalsePositive and FN – FalseNegative

10. What is Precision? Mention its formula.

Precision is defined as the percentage of true positive cases versus all the cases where the
prediction is true.

That is, it takes into account the True Positives and False Positives.

11. What is Recall? Mention its formula.

Recall is defined as the fraction of positive cases that are correctly identified.

12. Why is evaluation important? Explain

Evaluation is a process that critically examines a program. It involves collecting and analyzing
information about a program's activities, characteristics, and outcomes. Its purpose is to make
judgments about a program, to improve its effectiveness, and/or to inform programming
decisions.
 Evaluation is important to ensure that the model is operating correctly and optimally.
  Evaluation is an initiative to understand how well it achieves its goals.
 Evaluations help to determine what works well and what could be improved in a program

13. How do you suggest which evaluation metric is more important for any case?
F1 Evaluation metric is more important in any case. F1 score maintains a balance between the
precision and recall for the classifier. If the precision is low, the F1 is low and if the recall is low
again F1 score is low. The F1 score is a number between 0 and 1 and is the harmonic mean of
precision and recall.

When we have a value of 1 (that is 100%) for both Precision and Recall, the F1 score would also
be an ideal 1 (100%). It is known as the perfect value for F1 Score. As the values of both
Precision and Recall ranges from 0 to 1, the F1 score also ranges from 0 to 1.

14. Which evaluation metric would be crucial in the following cases?

Justify your answer.
a. Mail Spamming
b. Gold Mining
c. Viral Outbreak

a. If the model always predicts that the mail is spam, people would not look at it and eventually
might lose important information. False Positive condition would have a high cost. (predicting
the mail as spam while the mail is not spam) . Precision will be a crucial metric in this case.

b. A model saying that there exists treasure at a point and you keep on digging there but it turns
out that it is a false alarm. False Positive case is very costly. (Predicting there is a treasure but
there is no treasure). Precision will be a crucial metric in this case.

c. A deadly virus has started spreading and the model which is supposed to predict a viral
outbreak does not detect it. The virus might spread widely and infect a lot of people. Hence,
False Negative can be dangerous. Recall will be a crucial metric in this case.

15. What are the possible reasons for an AI model not being efficient? Explain.
Reasons of an AI model not being efficient:
a. Lack of Training Data: If the data is not sufficient for developing an AI Model, or if the data is
missed while training the model, it will not be efficient.
b. Unauthenticated Data / Wrong Data: If the data is not authenticated and correct, then the
model will not give good results.
c. Inefficient coding / Wrong Algorithms: If the written algorithms are not correct and relevant,
Model will not give desired output.
 d. Not Tested: If the model is not tested properly, then it will not be efficient.
e. Not Easy: If it is not easy to be implemented in production or scalable.
f. Less Accuracy: A model is not efficient if it gives less accuracy scores in production or test data
or if it is not able to generalize well on unseen data.

16. Give an example where High Accuracy is not usable

SCENARIO: An expensive robotic chicken crosses a very busy road a thousand times per day. An
ML model evaluates traffic patterns and predicts when this chicken can safely cross the street
with an accuracy of 99.99%.
Explanation: A 99.99% accuracy value on a very busy road strongly suggests that the ML model
is far better than chance. In some settings, however, the cost of making even a small number of
mistakes is still too high. 99.99% accuracy means that the expensive chicken will need to be
replaced, on average, every 10 days. (The chicken might also cause extensive damage to cars
that it hits.)

17. Give an example where High Precision is not usable

Example: “Predicting a mail as Spam or Not Spam”
False Positive: Mail is predicted as “spam” but it is “not spam”.
False Negative: Mail is predicted as “not spam” but it is “spam”.
Of course, too many False Negatives will make the spam filter ineffective but False Positives may
cause important mails to be missed and hence Precision is not usable.

18. Deduce the formula of F1 Score? What is the need of its formulation?
The F1 Score, also called the F score or F measure, is a measure of a test’s accuracy. It is
calculated from the precision and recall of the test. Precision is the number of correctly
identified positive results divided by the number of all positive results, including those not
identified correctly. Recall is the number of correctly identified positive results divided by the
number of all samples that should have been identified as positive.

The F1 score is defined as the weighted harmonic mean of the test’s precision and recall. This
score is calculated according to the formula:

F-Measure provides a single score that balances both the concerns of precision and recall in one
number. A good F1 score means that you have low false positives and low false negatives, so
you’re correctly identifying real threats, and you are not disturbed by false alarms. An F1 score is
considered perfect when it’s 1, while the model is a total failure when it’s 0. F1 Score is a better
metric to evaluate our model on real-life classification problems and when imbalanced class
distribution exists.

19. What is a confusion matrix? Explain in detail with the help of an example.
Confusion Matrix: A Confusion Matrix is a table that is often used to describe the performance
of a classification model (or "classifier") on a set of test data for which the true values are
known. A 2x2 matrix denoting the right and wrong predictions might help us analyse the rate of
success. This matrix is termed the Confusion Matrix.

Evaluation of the performance of a classification model is based on the counts of test records
correctly and incorrectly predicted by the model. Therefore, Confusion Matrix provides a more
insightful picture which is not only the performance of a predictive model, but also which
classes are being predicted correctly and incorrectly, and what type of errors are being made.
The confusion matrix is useful for measuring Recall (also known as Sensitivity), Precision,
Accuracy and F1 Score.

The following confusion matrix table illustrates how the 4-classification metrics are calculated
(TP, FP, FN, TN), and how our predicted value compared to the actual value in a confusion
matrix

The target variable has two values: Positive or Negative. The columns represent the actual
values of the target variable. The rows represent the predicted values of the target variable.

True Positive, True Negative, False Positive and False Negative in a Confusion Matrix
True Positive (TP)
The predicted value matches the actual value
The actual value was positive and the model predicted a positive value

True Negative (TN)

The predicted value matches the actual value.
The actual value was negative and the model predicted a negative value.

False Positive (FP) – Type 1 error

The predicted value was falsely predicted
The actual value was negative but the model predicted a positive value
Also known as the Type 1 error
False Negative (FN) – Type 2 error
The predicted value was falsely predicted
The actual value was positive but the model predicted a negative value
Also known as the Type 2 error

Example: Case: Loan (Good loan & Bad loan)

The result of TP will be that bad loans are correctly predicted as bad loans.
The result of TN will be that good loans are correctly predicted as good loans.
The result of FP will be that (actual) good loans are incorrectly predicted as bad loans.
The result of FN will be that (actual) bad loans are incorrectly predicted as good loans.

The banks would lose a bunch of money if the actual bad loans are predicted as good loans due
to loans not being repaid. On the other hand, banks won't be able to make more revenue if the
actual good loans are predicted as bad loans. Therefore, the cost of False Negatives is much
higher than the cost of False Positives.