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 1 of 3

1. Q1 CBSE 2026
   Statement 1 : Overfitting ​occurs ​when a model ​memorizes the training data rather ​than learning patterns. Statement ​2 : Using ​the same data for training and evaluation helps the model give accurate results.

   1. (a)Both statements are correct.
   2. (b)Both statements 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

   (c) Statement 1 is correct but statement 2 is incorrect.

   Step-by-step solution →
2. Q2 CBSE 2026
   A spam e-mail ​detection system correctly identifies an e-mail as ​“Not ​Spam” when it actually ​is not ​spam. This ​represents ​:

   1. (a)True Positive (TP)
   2. (b)True Negative (TN)
   3. (c)False Positive (FP)
   4. (d)False Negative (FN)
   Show answer

   (b) True Negative (TN)

   Step-by-step solution →
3. Q3 CBSE 2026
   In ​the ​context of autonomous ​vehicle ​safety systems, which type of ​error would be most ​critical ​to minimize ?

   1. (a)False Positive (detecting danger when there isn’t any)
   2. (b)False Negative (failing to detect actual danger)
   3. (c)True Positive (detecting danger correctly)
   4. (d)True Negative (correctly identifying that there is no danger)
   Show answer

   (b) False Negative (failing to detect actual danger)

   Step-by-step solution →
4. Q4 CBSE 2026
   Which ​of ​the following ​best describes ​overfitting ​in the ​context of train-test split ?

   1. (a)The model performs well on both training and test data.
   2. (b)The model performs well on training data but poorly on test data.
   3. (c)The model performs poorly on both training and test data.
   4. (d)The model performs poorly on training data but well on test data.
   Show answer

   (b) The model performs well on training data but poorly on test data.

   Step-by-step solution →
5. Q5 CBSE 2026
   In ​supervised learning, ​what is ​the purpose ​of the ​testing dataset ?

   1. (a)To train the model.
   2. (b)To evaluate the model’s accuracy.
   3. (c)To create new features.
   4. (d)To label the data.
   Show answer

   (b) To evaluate the model’s accuracy.

   Step-by-step solution →
6. Q6 CBSE 2026
   In a fire alarm system, ​if the model ​predicts ​“Fire Present” ​when ​there is actually ​no fire, this is classified as :

   1. (a)True Positive (TP)
   2. (b)True Negative (TN)
   3. (c)False Positive (FP)
   4. (d)False Negative (FN)
   Show answer

   (c) False Positive (FP)

   Step-by-step solution →
7. Q7 CBSE 2026
   Recall is a classification metrics ​that ​measures ​:

   1. (a)How many False positives are correctly identified by the model.
   2. (b)How many actual positive cases were correctly identified by the model.
   3. (c)How many negative cases were correctly identified by the model.
   4. (d)The overall accuracy of the model.
   Show answer

   (b) How many actual positive cases were correctly identified by the model.

   Step-by-step solution →
8. Q8 CBSE 2026
   Precision is defined as :

   1. (a)The ratio of correctly predicted positive observations to total observations.
   2. (b)The ratio of correctly predicted positive observations to total predicted positive observations.
   3. (c)The ratio of correctly predicted negative observations to total observations.
   4. (d)The harmonic mean of true positives and true negatives.
   Show answer

   (b) The ratio of correctly predicted positive observations to total predicted positive observations.

   Step-by-step solution →
9. Q9 CBSE 2026
   What ​is ​the primary ​purpose of train-test ​split in ​model ​evaluation ?

   1. (a)To increase the size of the dataset.
   2. (b)To reduce computational complexity.
   3. (c)To estimate the performance of the machine learning model on new data.
   4. (d)To improve the accuracy of the training process.
   Show answer

   (c) To estimate the performance of the machine learning model on new data.

   Step-by-step solution →
10. Q10 CBSE 2026
    In ​machine learning, ​the error is ​used ​to see ​how accurately the model can ​predict data.
    Show answer

    True

    Step-by-step solution →
11. Q11 CBSE 2026
    This ethical concern refers to an ​honest explanation how ​the ​chosen evaluation metrics work and produce results without keeping any information hidden. Name this ethical ​concern that ​should be kept in mind while evaluating ​an ​AI model.

    1. (a)Bias
    2. (b)Transparency
    3. (c)Accountability
    4. (d)Accuracy
    Show answer

    (b) Transparency

    Step-by-step solution →
12. Q12 CBSE 2026
    An AI ​model was tested with 1000 test samples. If True Positive (TP) = 200, True Negative (TN) = 600, False ​Positive ​(FP) = 100, False ​Negative (FN) = 100, ​how ​many total predictions were correct ​?

    1. (a)300
    2. (b)600
    3. (c)800
    4. (d)900
    Show answer

    (c) 800

    Step-by-step solution →
13. Q13 CBSE 2026
    Which ​of ​the ​following ​best ​describes ​model evaluation ​in artificial ​intelligence ?

    1. (a)The process of creating new datasets for training
    2. (b)The process of using different evaluation metrics to understand a machine learning model’s performance
    3. (c)The process of selecting algorithms for model building
    4. (d)The process of data preprocessing and cleaning
    Show answer

    (b) The process of using different evaluation metrics to understand a machine learning model’s performance

    Step-by-step solution →
14. Q14 CBSE 2026
    Explain ​Train-test split ​technique ​with respect ​to ​machine learning algorithm.
    Show answer

    The dataset is split into a training set, which makes the model learn, and a testing set, which evaluates it.

    Train-test split divides a dataset into a training set that makes the model learn and a testing set that evaluates its performance on new, unseen data, usually split $80:20$.

    Step-by-step solution →
15. Q15 CBSE 2026
    Define Accuracy. Also give ​one example to explain ​why high ​accuracy does not ​always mean a ​model is performing ​well ​in ​real-world situations.
    Show answer

    Accuracy is the fraction of correct predictions; a test calling every patient healthy is $99\%$ accurate yet detects no ill patient.

    Accuracy is the evaluation metric measuring the fraction of predictions a model gets right. A disease test calling every patient healthy is $99\%$ accurate yet detects no ill patient.

    Step-by-step solution →
16. Q16 CBSE 2026
    Read the following paragraph and answer the questions that follow : PQR Security Solutions has designed an AI Model to detect cyber attacks on ​E-Commerce websites. For this, various network ​activities were monitored and analyzed ​on one of the ​websites. The model was tested on a dataset of 1500 network activities. Out ​of these, the model correctly predicted that 1000 were cyber attacks. ​It also correctly identified that 250 ​were not cyber attacks. However, the model predicted that ​200 were cyber attacks but actually they were not. Additionally, it predicted that 50 were not cyber attacks but they actually were.

    1. (A)Draw the confusion matrix based on the given scenario.[2]
    2. (B)How many total cases are True Negative in the above scenario ?[1]
    3. (C)Calculate Precision.[1]
    Show answer

    TP 1000, FP 200, FN 50 and TN 250; True Negatives are 250 and Precision is $0.833$.

    (A) The confusion matrix has Prediction down the rows and Reality across the columns: Prediction Yes with Reality Yes is $\text{TP}=1000$, Prediction Yes with Reality No is $\text{FP}=200$, Prediction No with Reality Yes is $\text{FN}=50$, and Prediction No with Reality No is $\text{TN}=250$. (B) True Negative $=250$ cases. (C) Precision $=\frac{\text{TP}}{\text{TP}+\text{FP}}=\frac{1000}{1200}=0.833=83.3\%$.

    Step-by-step solution →
17. Q17 CBSE 2026
    An AI model has been developed to predict whether electric vehicle ​batteries need replacement based on performance data. The model was tested on a dataset of ​700 vehicles and the ​resulting confusion matrix is as follows : $$\begin{array}{lcc}\text{Confusion Matrix}& \text{Reality: Yes}& \text{Reality: No}\\ \text{Prediction: Yes}& 590& 20\\ \text{Prediction: No}& 10& 80\end{array}$$ The above Confusion Matrix ​can also be represented ​as follows :

    Actual Values	Predicted Values: 1	Predicted Values: 0
    1	590	10
    0	20	80

    1. (a)How many total cases are False Positives in the above scenario ?[1]
    2. (b)Calculate Precision, Recall and F1 Score.[3]
    Show answer

    False Positives are 20; Precision is $0.967$, Recall is $0.983$ and F1 Score is $0.975$.

    (a) The False Positives are the $20$ vehicles the model predicted needed replacement when in reality they did not. (b) Taking $\text{TP}=590$, $\text{FP}=20$ and $\text{FN}=10$ from the matrix: Precision $=\frac{\text{TP}}{\text{TP}+\text{FP}}=\frac{590}{610}=0.967$. Recall $=\frac{\text{TP}}{\text{TP}+\text{FN}}=\frac{590}{600}=0.983$. F1 Score $=\frac{2\times \text{TP}}{2\times \text{TP}+\text{FP}+\text{FN}}=\frac{1180}{1210}=0.975$.

    Step-by-step solution →
18. Q18 CBSE 2025
    _________ ​is ​defined ​as the ​percentage ​of ​correct predictions out of all ​the observations.

    1. (a)Precision
    2. (b)Accuracy
    3. (c)Recall
    4. (d)F1
    Show answer

    (b) Accuracy

    Step-by-step solution →
19. Q19 CBSE 2025
    In ​a quality ​control system for ​manufacturing, ​which ​scenario ​represents a false negative ​?

    1. (a)When a defective product is correctly identified as defective.
    2. (b)When a non-defective product is inaccurately identified as defective.
    3. (c)When a non-defective product is correctly identified as non-defective.
    4. (d)When a defective product is mistakenly identified as non-defective.
    Show answer

    (d) When a defective product is mistakenly identified as non-defective.

    Step-by-step solution →
20. Q20 CBSE 2025
    Which ​condition of ​evaluation does the following ​diagram ​indicate ​?

    1. (a)False Positive
    2. (b)False Negative
    3. (c)True Positive
    4. (d)True Negative
    Show answer

    (b) False Negative

    Step-by-step solution →