Class 10 Artificial Intelligence

Evaluating Models

51 Class 10 Artificial Intelligence questions on Evaluating Models from the CBSE board papers 2022–2026, each with its answer and a step-by-step solution.

Questions · page 2 of 3

Q21 CBSE 2025
Statement 1 : Overfitting is not recommended for evaluation of a model. Statement 2 : This is because the model will simply remember the whole training set, and will therefore always predict the correct label for any point in the training set.
1. (a)Both Statement 1 and Statement 2 are correct.
2. (b)Both Statement 1 and Statement 2 are incorrect.
3. (c)Statement 1 is correct but Statement 2 is incorrect.
4. (d)Statement 2 is correct but Statement 1 is incorrect.
Show answer

(a) Both Statement 1 and Statement 2 are correct.

Step-by-step solution →
Q22 CBSE 2025
It is one of the parameters for evaluating a model’s performance and is defined as the percentage of true positive cases versus all the cases where the prediction is true. Which of the following evaluation parameter is this ?
1. (a)Precision
2. (b)Recall
3. (c)F1 score
4. (d)Accuracy
Show answer

(a) Precision

Step-by-step solution →
Q23 CBSE 2025

When a model is evaluated on the training data it always predicts correctly. This is known as ___________.

Show answer

Overfitting. The model has fitted its training data too closely, so it repeats those answers perfectly and performs poorly on data it has not seen.

Step-by-step solution →
Q24 CBSE 2025
Which of the following is not true about Confusion Matrix ?
1. (a)It allows us to understand prediction results.
2. (b)It is a Model Training Matrix.
3. (c)It helps in evaluation of machine learning models.
4. (d)It is used to record comparison between prediction and reality.
Show answer

(b) It is a Model Training Matrix.

Step-by-step solution →
Q25 CBSE 2025
With respect to evaluation, for which of the following does the prediction and reality match ?
1. (a)True positive and False positive
2. (b)True positive and True negative
3. (c)False positive and False negative
4. (d)True positive and False negative
Show answer

(b) True positive and True negative

Step-by-step solution →
Q26 CBSE 2025
Which of the following scenarios might have a high False Negative (FN) cost ?
1. (a)Viral Disease Outbreak
2. (b)Spam
3. (c)Mining
4. (d)Image Search
Show answer

(a) Viral Disease Outbreak

Step-by-step solution →
Q27 CBSE 2025
In a medical screening test for a specific disease, which scenario represents a True Negative ?
1. (a)A person without the disease tests positive for the disease.
2. (b)A person with the disease tests positive for the disease.
3. (c)A person with the disease tests negative for the disease.
4. (d)A person without the disease tests negative for the disease.
Show answer

(d) A person without the disease tests negative for the disease.

Step-by-step solution →
Q28 CBSE 2025
Draw the confusion matrix for the following data :
1. (a)The number of true positive $= 200$
2. (b)The number of true negative $= 50$
3. (c)The number of false positive $= 35$
4. (d)The number of false negative $= 55$
Show answer

The matrix has TP 200 and FP 35 in the Prediction Yes row, and FN 55 and TN 50 in the Prediction No row.
The confusion matrix below has Prediction down the rows and Reality across the columns, Yes before No. Top row (Prediction Yes): $TP = 200$ , $FP = 35$ . Bottom row (Prediction No): $FN = 55$ , $TN = 50$ .

Step-by-step solution →
Q29 CBSE 2025

Suppose you are developing an AI model to detect fraudulent financial transaction risk. Describe False Positives and False Negatives in this context.

Show answer

A false positive wrongly flags a genuine transaction as fraud; a false negative lets a fraudulent transaction pass undetected.
Positive means the model predicts fraud. False Positive: a genuine transaction is wrongly flagged as fraudulent, losing customer trust. False Negative: a fraudulent transaction goes undetected, causing financial loss.

Step-by-step solution →
Q30 CBSE 2025
An AI model has been developed to test specimens of blood/urine/cough etc. to diagnose ailments (diabetes/liver infection etc.). The model was tested on a data-set of about 630 tests and the resulting confusion matrix is as follows :
Confusion Matrix Reality: Yes Reality: No
Prediction: Yes 110 60
Prediction: No 50 410
1. (A)How many total cases are True Negative in the above scenario ?[1]
2. (B)Calculate Precision, Recall and F1 Score.[3]
Show answer

True Negatives are 410; Precision is $0.647$ , Recall is $0.688$ and F1 Score is $0.667$ .
(A) The True Negative cases are the $410$ specimens the model reported as No when the reality was also No. (B) Taking $TP = 110$ , $FP = 60$ and $FN = 50$ from the matrix: Precision $= \frac{TP}{TP + FP} = \frac{110}{170} = 0.647$ . Recall $= \frac{TP}{TP + FN} = \frac{110}{160} = 0.688$ . F1 Score $= \frac{2 \times TP}{2 \times TP + FP + FN} = \frac{220}{330} = 0.667$ .

Step-by-step solution →
Q31 CBSE 2025
A sentiment analysis model was built to classify movie reviews as either ‘Positive’ or ‘Negative’. The model was tested on a dataset of 500 reviews, resulting in the following confusion matrix :
Confusion Matrix Reality: Yes Reality: No
Predicted: Yes 300 40
Predicted: No 60 100
1. (a)How many total cases are True Positive in the above scenario ?[1]
2. (b)Calculate Precision, Recall and F1-Score.[3]
Show answer

300 True Positives; Precision is $0.882$ , Recall is $0.833$ and F1 Score is $0.857$ .
(a) The True Positive cases are the $300$ reviews the model predicted as positive when the reality was also positive. (b) With $TP = 300$ , $FP = 40$ and $FN = 60$ : Precision $= \frac{300}{300 + 40} = \frac{300}{340} = 0.882$ . Recall $= \frac{300}{300 + 60} = \frac{300}{360} = 0.833$ . F1 Score $= \frac{2 \times \frac{300}{340} \times \frac{300}{360}}{\frac{300}{340} + \frac{300}{360}} = \frac{600}{700} = 0.857$ .

Step-by-step solution →
Q32 CBSE 2024
_________ is one of the parameter for evaluating a model’s performance and is defined as the fraction of positive cases that are correctly identified.
1. (a)Precision
2. (b)Accuracy
3. (c)Recall
4. (d)F1
Show answer

(c) Recall

Step-by-step solution →
Q33 CBSE 2024
In spam email detection, which of the following will be considered as “False Negative” ?
1. (a)When a legitimate email is accurately identified as not spam.
2. (b)When a spam email is mistakenly identified as legitimate.
3. (c)When an email is accurately recognised as spam.
4. (d)When an email is inaccurately labelled as important.
Show answer

(b) When a spam email is mistakenly identified as legitimate.

Step-by-step solution →
Q34 CBSE 2024
Statement 1 : Confusion matrix is an evaluation metric. Statement 2 : Confusion Matrix is a record which helps in evaluation.
1. (a)Both Statement 1 and Statement 2 are correct.
2. (b)Both Statement 1 and Statement 2 are incorrect.
3. (c)Statement 1 is correct and Statement 2 is incorrect.
4. (d)Statement 2 is correct and Statement 1 is incorrect.
Show answer

(d) Statement 2 is correct and Statement 1 is incorrect.

Step-by-step solution →
Q35 CBSE 2024
What is the primary need for evaluating an AI model’s performance in the AI Model Development process ?
1. (a)To increase the complexity of the model.
2. (b)To visualize the data.
3. (c)To assess how well the chosen model will work in future.
4. (d)To reduce the amount of data used for training.
Show answer

(c) To assess how well the chosen model will work in future.

Step-by-step solution →
Q36 CBSE 2024
Statement 1 : To evaluate a models’ performance, we need either precision or recall. Statement 2 : When the value of both Precision and Recall is 1, the F1 score is 0.
1. (a)Both statement 1 and statement 2 are correct.
2. (b)Both statement 1 and statement 2 are incorrect.
3. (c)Statement 1 is correct, but statement 2 is incorrect.
4. (d)Statement 1 is incorrect, but statement 2 is correct.
Show answer

(b) Both statement 1 and statement 2 are incorrect.

Step-by-step solution →
Q37 CBSE 2024

What do you mean by Evaluation of an AI model ? Also explain the concept of overfitting with respect to AI model Evaluation.

Show answer

Evaluation compares a model's outputs on test data with actual answers; overfitting is when a model tested on its training data remembers it.
Evaluation checks a model's reliability by feeding it test data and comparing outputs with actual answers. Overfitting: evaluated on its training data, the model remembers it and always predicts correctly.

Step-by-step solution →
Q38 CBSE 2024
A binary classification model has been developed to classify news articles as either “Fake News” or “Real News”. The model was tested on a dataset of 500 news articles, and the resulting confusion matrix is as follows :
Confusion Matrix Reality: Yes Reality: No
Predicted: Yes 45 15
Predicted: No 20 420
1. (A)How many total cases are True Negative in the above scenario ?[1]
2. (B)Calculate Precision, Recall and F1-Score.[3]
Show answer

True Negatives are 420; Precision is $0.750$ , Recall is $0.692$ and F1 Score is $0.720$ .
(A) The True Negative cases are the $420$ articles the model predicted as No when the reality was also No. (B) With $TP = 45$ , $FP = 15$ and $FN = 20$ : Precision $= \frac{45}{45 + 15} = \frac{45}{60} = 0.750$ . Recall $= \frac{45}{45 + 20} = \frac{45}{65} = 0.692$ . F1 Score $= \frac{2 \times 0.750 \times 0.692}{0.750 + 0.692} = \frac{90}{125} = 0.720$ .

Step-by-step solution →
Q39 CBSE 2023
Which of the following is defined as the measure of balance between precision and recall ?
1. (a)Accuracy
2. (b)F1 Score
3. (c)Reliability
4. (d)Punctuality
Show answer

(b) F1 Score

Step-by-step solution →
Q40 CBSE 2023

_________ helps to find the best model that represents our data and how well the chosen model will work in future.

Show answer

Evaluation. It is the stage of the AI project cycle that tests the trained models on data they have not seen, so that the model which best represents the data can be chosen and its future performance judged.

Step-by-step solution →

Confusion Matrix	Reality: Yes	Reality: No
Prediction: Yes	110	60
Prediction: No	50	410

Confusion Matrix	Reality: Yes	Reality: No
Predicted: Yes	300	40
Predicted: No	60	100

Confusion Matrix	Reality: Yes	Reality: No
Predicted: Yes	45	15
Predicted: No	20	420