Evaluating Models MCQs with Answers – Class 10 AI (417)
Want top marks in Class 10 AI (417)?
These Evaluating Models MCQs are a must-practice! these are simple, exam-ready questions made from the latest CBSE syllabus, past paper patterns, and key concepts. Practice them and build rock-solid concepts, revise super fast, and walk into the exam with full confidence!
Don’t just study—master the exam! 🎓✨ Start practicing these MCQs today.
MULTIPLE CHOICE QUESTIONS (MCQs) – Evaluating Models
Q1. Which stage of the AI Project Cycle checks how well an AI model performs?
a) Problem Scoping
b) Data Acquisition
c) Model Evaluation
d) Data Exploration
Q2. Model evaluation is mainly used to:
a) Collect data
b) Improve model performance
c) Store data
d) Create websites
Q3. An AI model improves with:
a) Random guessing
b) Constructive feedback
c) More advertisements
d) Less training
Q4. Model evaluation is similar to a student’s:
a) Notebook
b) Attendance
c) Report card
d) Homework
Q5. Which dataset is used for training the model?
a) Testing dataset
b) Validation dataset
c) Training dataset
d) Sample dataset
Q6. The purpose of the testing dataset is to:
a) Train the model
b) Evaluate model performance
c) Collect data
d) Store predictions
Q7. The train-test split divides the data into:
a) Three parts
b) Two parts
c) Four parts
d) Five parts
Q8. Which problem occurs if the model is evaluated using the same data on which it was trained?
a) Underfitting
b) Overfitting
c) Clustering
d) Regression
Q9. Accuracy measures:
a) Total errors
b) Correct predictions
c) Incorrect predictions
d) Data size
Q10. Error represents:
a) Correct prediction
b) Difference between prediction and actual value
c) Training data
d) Dataset size
Q11. A good AI model should:
a) Maximize error
b) Minimize accuracy
c) Maximize accuracy
d) Ignore evaluation
Q12. In machine learning, error helps us:
a) Delete data
b) Select the better-performing model
c) Create datasets
d) Increase memory
Q13. Which evaluation metric counts the total correct predictions?
a) Recall
b) Precision
c) Accuracy
d) F1 Score
Q14. Classification means:
a) Predicting numerical values
b) Dividing data into categories
c) Collecting data
d) Removing errors
Q15. Which of the following is a classification problem?
a) House price prediction
b) Salary prediction
c) Credit card fraud detection
d) Temperature prediction
Q16. A confusion matrix is mainly used for:
a) Regression
b) Classification
c) Clustering
d) Data cleaning
Q17. In a confusion matrix, the rows generally represent:
a) Predicted values
b) Actual values
c) Accuracy
d) Precision
Q18. The columns in a confusion matrix represent:
a) Actual values
b) Training data
c) Predicted values
d) Features
Q19. Which metric becomes less reliable for highly unbalanced datasets?
a) Precision
b) Recall
c) Accuracy
d) F1 Score
Q20. Which metric combines Precision and Recall?
a) Accuracy
b) Error
c) F1 Score
d) Confusion Matrix
Q21. What is the main objective of model evaluation?
a) Increase storage
b) Find the best-performing model
c) Remove datasets
d) Increase training data
Q22. Train-test split is suitable when:
a) Dataset is very small
b) Dataset is sufficiently large
c) Dataset has no labels
d) Dataset is empty
Q23. Overfitting occurs because the model:
a) Learns only new data
b) Memorizes training data
c) Deletes testing data
d) Uses random predictions
Q24. Which statement about accuracy is correct?
a) Better accuracy indicates better model performance.
b) Lower accuracy means better performance.
c) Accuracy measures only errors.
d) Accuracy is unrelated to prediction quality.
Q25. In medical diagnosis, wrongly predicting a healthy person as sick is called:
a) True Positive
b) False Positive
c) False Negative
d) True Negative
Q26. True Positive means:
a) Correctly predicting the positive class
b) Correctly predicting the negative class
c) Incorrectly predicting the positive class
d) Incorrectly predicting the negative class
Q27. True Negative means:
a) Wrongly predicting positive
b) Correctly predicting negative
c) Wrongly predicting negative
d) Predicting both classes
Q28. False Positive occurs when:
a) Negative class is predicted as positive
b) Positive class is predicted as negative
c) Positive is predicted correctly
d) Negative is predicted correctly
Q29. False Negative occurs when:
a) Positive class is predicted as negative
b) Negative class is predicted as positive
c) Positive class is predicted correctly
d) Negative class is predicted correctly
Q30. Which formula gives classification accuracy?
a) TP/(TP+FP)
b) TP/(TP+FN)
c) (TP+TN)/(TP+TN+FP+FN)
d) FP/(TP+FP)
Q31. Precision mainly focuses on reducing:
a) True Positives
b) False Positives
c) False Negatives
d) True Negatives
Q32. Recall mainly focuses on reducing:
a) False Positives
b) False Negatives
c) True Negatives
d) Accuracy
Q33. Precision is calculated as:
a) TP/(TP+FP)
b) TP/(TP+FN)
c) TN/(TN+FN)
d) FP/(FP+FN)
Q34. Recall is calculated as:
a) TP/(TP+FP)
b) TP/(TP+FN)
c) TN/(TN+FP)
d) FP/(TP+FN)
Q35. Precision tells us:
a) Out of all predicted positives, how many are actually positive.
b) Out of all actual positives, how many are predicted positive.
c) Total number of predictions.
d) Total number of errors.
Q36. Recall tells us:
a) Total predictions
b) Out of all actual positives, how many are correctly identified.
c) Total errors
d) Dataset size
Q37. Recall is also known as:
a) Accuracy Rate
b) Sensitivity
c) Precision Rate
d) Error Rate
Q38. F1 Score is useful when:
a) Dataset is balanced
b) Only accuracy matters
c) Both Precision and Recall are important
d) No evaluation is required
Q39. Which metric should be preferred when False Positives are costly?
a) Accuracy
b) Precision
c) Recall
d) Error
Q40. Which metric should be preferred when False Negatives are costly?
a) Precision
b) Accuracy
c) Recall
d) Error
Q41. A weather prediction model is used to decide whether a satellite should be launched. Predicting bad weather as good weather should be avoided. Which metric is most suitable?
a) Accuracy
b) Precision
c) Recall
d) Error
Q42. A COVID-19 detection model should minimize:
a) True Positives
b) True Negatives
c) False Negatives
d) False Positives
Q43. Which metric is most appropriate for a COVID-19 detection system?
a) Accuracy
b) Precision
c) Recall
d) Error Rate
Q44. In fraud detection, a fraudulent transaction predicted as legitimate is:
a) True Positive
b) False Positive
c) False Negative
d) True Negative
Q45. For credit card fraud detection, which metric is more important?
a) Recall
b) Accuracy
c) Error Rate
d) Mean Error
Q46. A model correctly predicts 90 out of 100 test cases. Its accuracy is:
a) 80%
b) 85%
c) 90%
d) 95%
Q47. Which statement is TRUE?
a) Accuracy is always the best metric.
b) Precision and Recall are useful for unbalanced datasets.
c) Confusion matrix is used only for regression.
d) F1 Score ignores Recall.
Q48. Which evaluation metric uses both Precision and Recall?
a) Accuracy
b) Error Rate
c) F1 Score
d) Train-Test Split
Q49. If Precision is high, it means:
a) The model makes fewer False Positive predictions.
b) The model makes more False Negatives.
c) The model ignores positive cases.
d) The model always predicts negative.
Q50. Which statement best explains model evaluation?
a) It is used only before model training.
b) It measures how well a model performs and helps improve it.
c) It replaces model training.
d) It is used only for collecting data.
Q51. In a medical test for a rare disease, out of 1000 people tested, 50 actually have the disease while 950 do not. The test correctly identifies 40 out of the 50 people with the disease as positive, but it also wrongly identifies 30 of the healthy individuals as positive. What is the accuracy of the test?
a) 97%
b) 90%
c) 85%
d) 70%
Q52. A student solved 90 out of 100 questions correctly in a multiple-choice exam. What is the error rate of the student’s answers?
a) 10%
b) 9%
c) 8%
d) 11%
Q53. In a spam email detection system, out of 1000 emails received, 300 are spam. The system correctly identifies 240 spam emails as spam, but it also marks 60 legitimate emails as spam. What is the precision of the system?
a) 80%
b) 70%
c) 75%
d) 90%
Q54. In a binary classification problem, a model predicts 70 instances as positive out of which 50 are actually positive. What is the recall of the model?
a) 50%
b) 70%
c) 80%
d) 100%
Q55. In a sentiment analysis task, a model correctly predicts 120 positive sentiments out of 200 positive instances. However, it also incorrectly predicts 40 negative sentiments as positive. What is the F1-score of the model?
a) 0.80
b) 0.75
c) 0.72
d) 0.82
Q56. A medical diagnostic test is designed to detect a certain disease. Out of 1000 people tested, 100 have the disease, and the test identifies 90 of them correctly. However, it also wrongly identifies 50 healthy people as having the disease. What is the precision of the test?
a) 90%
b) 80%
c) 70%
d) 60%
Q57. A teacher’s marks prediction system predicts the marks of a student as 75, but the actual marks obtained by the student are 80. What is the absolute error in the prediction?
a) 5
b) 10
c) 15
d) 20
Q58. The goal when evaluating an AI model is to:
a) Maximize error and minimize accuracy
b) Minimize error and maximize accuracy
c) Focus solely on the number of data points used
d) Prioritize the complexity of the model
Q59. A high F1-score generally suggests:
a) A significant imbalance between precision and recall
b) A good balance between precision and recall
c) A model that only performs well on specific data points
d) The need for more training data
Q60. How is the relationship between model performance and accuracy described?
a) Inversely proportional
b) Not related
c) Directly proportional
d) Randomly fluctuating
ASSERTION AND REASON BASED QUESTIONS – Evaluating Models
Q61. Assertion (A): Model evaluation helps in selecting the best AI model.
Reason (R): Different evaluation metrics are used to measure a model’s performance.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q62. Assertion (A): An AI model improves with constructive feedback.
Reason (R): Evaluation metrics help identify the strengths and weaknesses of a model.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q63. Assertion (A): The training dataset is used to evaluate the model.
Reason (R): The testing dataset is used to check the performance of a trained model.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q64. Assertion (A): Using the same data for training and testing may lead to overfitting.
Reason (R): The model may simply memorize the training data instead of learning patterns.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q65. Assertion (A): Accuracy is always the best metric for evaluating classification models.
Reason (R): Accuracy may give misleading results for unbalanced datasets.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q66. Assertion (A): A confusion matrix is used to evaluate classification models.
Reason (R): It shows the number of correct and incorrect predictions made by a model.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q67. Assertion (A): True Positive means the model correctly predicts the positive class.
Reason (R): False Positive means the model correctly predicts the negative class.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q68. Assertion (A): Precision becomes important when False Positives should be minimized.
Reason (R): Precision measures the proportion of correctly predicted positive cases among all predicted positive cases.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q69. Assertion (A): Recall is useful in disease detection models.
Reason (R): Recall focuses on reducing False Negatives.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q70. Assertion (A): Recall is also known as Sensitivity.
Reason (R): Recall measures how many actual positive cases are correctly identified.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q71. Assertion (A): F1 Score combines Precision and Recall.
Reason (R): F1 Score is useful when both False Positives and False Negatives are important.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q72. Assertion (A): Credit card fraud detection requires high Recall.
Reason (R): Missing a fraudulent transaction (False Negative) can cause serious financial loss.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q73. Assertion (A): Classification accuracy is calculated using only True Positives.
Reason (R): Accuracy includes both True Positives and True Negatives.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q74. Assertion (A): Error represents the difference between predicted and actual values.
Reason (R): A lower error generally indicates a better-performing model.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
Q75. Assertion (A): Precision and Recall are mainly preferred for balanced datasets.
Reason (R): These metrics are especially useful for unbalanced datasets.
a) Both Assertion (A) and Reason (R) are true, and R is the correct explanation of A.
b) Both Assertion (A) and Reason (R) are true, but R is NOT the correct explanation of A.
c) Assertion (A) is true, but Reason (R) is false.
d) Assertion (A) is false, but Reason (R) is true.
