ISQI ISQI-CT-AI Online Practice Questions and Exam Preparation

ISQI ISQI-CT-AI Online Questions & Answers

• Question 81:

  Which of the following is one of the reasons for data mislabelling?

  A. Lack of domain knowledge
  B. Expert knowledge
  C. Interoperability error
  D. Small datasets
  A. Lack of domain knowledge

  ---

• Question 82:

  Which ONE of the following is the MOST appropriate metric to prioritize for a cancer detection system with very low prevalence?

  A. Accuracy
  B. Recall
  C. Specificity
  D. R-squared
  B. Recall

  ---

• Question 83:

  A system was developed for screening X-ray images of patients for potential malignancy detection (skin cancer). A workflow system has been developed to screen multiple cancers by using several individually trained ML models chained together in a workflow. Testing the pipeline could involve multiple kinds of tests (I-III):

  A. Pairwise testing of combinations II. Testing each individual model for accuracy III. A/B testing of different sequences of models Which ONE of the following options contains the kinds of tests that would be MOST APPROPRIATE to include in the strategy for optimal detection?
  B. Only III
  C. I and II
  D. I and III
  E. Only II
  B. Only III

  ---

  For an ML workflow composed of multiple chained models, an effective testing strategy must address both individual model performance and interactions between models.

  Testing each individual model for accuracy (II) is essential to ensure that every component in the workflow meets its functional performance requirements before integration.

  Pairwise testing of combinations (I) helps identify interaction issues between models in the workflow, which is important when multiple ML components are combined.

  While A/B testing of different model sequences (III) can be useful for optimization, it is not as fundamental as validating individual model accuracy and critical interactions when establishing reliable detection performance.

  Therefore, the most appropriate combination of tests is I and II, making Option B the correct answer.

• Question 84:

  Which ONE of the following options BEST DESCRIBES clustering?

  A. Clustering is classification of a continuous quantity.
  B. Clustering is supervised learning.
  C. Clustering is done without prior knowledge of output classes.
  D. Clustering requires prior knowledge of the classes.
  C. Clustering is done without prior knowledge of output classes.

  ---

  The ISTQB CT-AI syllabus defines clustering as an unsupervised learning technique in which data points are grouped based on similarity, without using labeled output classes. The goal of clustering is to discover inherent structures or patterns in the data.

  Option C correctly reflects this definition, stating that clustering is performed without prior knowledge of output classes.

  The other options are incorrect. Classification of continuous quantities refers to regression, not clustering. Clustering is not supervised learning, and it does not require prior knowledge of classes.

  Therefore, Option C is the correct answer.

• Question 85:

  Which ONE of the following types of coverage SHOULD be used if test cases need to cause each neuron to achieve both positive and negative activation values?

  A. Value coverage
  B. Threshold coverage
  C. Sign change coverage
  D. Neuron coverage
  C. Sign change coverage

  ---

  Coverage for Neuron Activation Values: Sign change coverage is used to ensure that test cases cause each neuron to achieve both positive and negative activation values. This type of coverage ensures that the neurons are thoroughly tested under different activation states. Reference: ISTQB_CT-AI_Syllabus_v1.0, Section 6.2 Coverage Measures for Neural Networks, which details different types of coverage measures, including sign change coverage.

• Question 86:

  Written requirements are provided in textual documents. Which ONE of the following options is the BEST way to generate test cases from these requirements?

  A. Natural language processing on textual requirements
  B. Analyzing source code for generating test cases
  C. Machine learning on logs of execution
  D. GUI analysis using computer vision
  A. Natural language processing on textual requirements

  ---

  The ISTQB CT-AI syllabus explains that when requirements are available in natural language text, the most appropriate AI-based technique for generating test cases is Natural Language Processing (NLP). NLP techniques can analyze textual requirements, identify relevant entities, conditions, and constraints, and support the automated derivation of test cases from written specifications.

  The other options are less suitable in this context. Source code analysis is applicable to white-box testing and requires implemented code. Machine learning on execution logs depends on runtime behavior rather than written requirements.

  GUI analysis using computer vision focuses on visual interfaces, not textual requirement documents.

  Therefore, Natural language processing on textual requirements is the best approach.

• Question 87:

  Which of the following options is an example of the concept of overfitting?

  A. A model for predicting academic performance was trained with data from students at one university. The model shows low predictive accuracy when applied to other universities.
  B. A model for the recognition of dogs was trained predominantly with pictures of dogs in parks. On pictures with other animals in parks, dogs are also falsely recognized.
  C. A previously trained model for recognizing cars is adapted and extended so that it can also identify the make of the car beyond its original function.
  D. A model for predicting IT system failures delivers too many false-negative predictions because the failures cannot be adequately explained via the log files used for training.
  A. A model for predicting academic performance was trained with data from students at one university. The model shows low predictive accuracy when applied to other universities.

  ---

  The ISTQB CT- AI syllabus defines overfitting in Section 3.2 - ML Model Evaluation as a condition where a machine learning model learns the training data too precisely---including noise and irrelevant detail---resulting in poor performance on unseen data. Overfitting is characterized by high accuracy on the training data but low accuracy on validation data or real-world data. Option A perfectly matches this definition: a model trained only on one university's student data generalizes poorly to students from

  other universities. This is a textbook example of overfitting because the model has effectively memorized patterns specific to a narrow data set rather than learning generalizable relationships applicable across environments.

  Option B describes sample bias or insufficient diversity in the training data rather than overfitting. Option C involves transfer learning or model extension and is unrelated to overfitting. Option D indicates insufficient training data quality or inadequate features but does not represent overfitting. Only Option A directly reflects the syllabus definition of overfitting: overly specialized training leading to reduced predictive performance on new data.

  Thus, Option A is the correct and syllabus-aligned example of overfitting.

• Question 88:

  Which ONE of the following BEST describes back-to-back testing in the context of AI systems?

  A. Comparing system outputs against manually defined expected results
  B. Comparing outputs of two different implementations using the same inputs
  C. Executing tests repeatedly to obtain statistically valid results
  D. Testing extreme input values to identify boundary failures
  B. Comparing outputs of two different implementations using the same inputs

  ---

• Question 89:

  A bank wants to use an algorithm to determine which applicants should be given a loan. The bank hires a data scientist to construct a logistic regression model to predict whether an applicant will repay the loan or not. The bank has enough data on past customers to randomly split the data into a training data set and a test/validation data set. A logistic regression model is constructed on the training data set using the following independent variables:

  Gender Marital status Number of dependents Education Income Loan amount Loan term Credit score

  The model reveals that applicants with higher credit scores and higher total incomes are more likely to repay their loans. The data scientist has suggested that there might be bias present in the model based on previous models created for other banks.

  Given this information, what is the best test approach to check for potential bias in the model?

  A. Experience-based testing should be used to confirm that the training data set is operationally relevant. This can include applying exploratory data analysis (EDA) to check for bias within the training data set.
  B. Back-to-back testing should be used to compare the model created using the training data set with another model created using the test data set. If the two models significantly differ, it will indicate that there is bias in the original model.
  C. Acceptance testing should be used to ensure that the algorithm is suitable for customers. The team can rework the acceptance criteria so that the algorithm correctly predicts the remaining applicants in the validation data set, ensuring that no bias is present.
  D. A/B testing should be used to verify that the test data set does not detect any bias that might have been introduced by the original training data. If the two models significantly differ, it will indicate that there is bias in the original model.
  A. Experience-based testing should be used to confirm that the training data set is operationally relevant. This can include applying exploratory data analysis (EDA) to check for bias within the training data set.

  ---

  The ISTQB CT-AI syllabus explains that experience-based testing and exploratory data analysis (EDA) are effective techniques for identifying potential bias in training data and models. Experience-based testing can be used to verify that the training data set is operationally relevant and representative of the real-world population. EDA supports this by enabling testers to explore distributions, correlations, and patterns in the data that may reveal imbalances or relationships leading to bias.

  This directly supports Option A, which combines experience-based testing with EDA to assess bias in the training data and, by extension, in the resulting model.

  The other options are incorrect. Back-to-back testing and A/B testing are not appropriate methods for detecting bias in training data; differences between models do not necessarily indicate bias. Acceptance testing focuses on stakeholder requirements and suitability, not on identifying bias in data or models.

• Question 90:

  You have access to the training data that was used to train an AI-based system. You can review this information and use it as a guideline when creating your tests. What type of characteristic is this?

  A. Autonomy
  B. Explorability
  C. Transparency
  D. Accessibility
  C. Transparency

  ---

  "Transparency: This is considered to be the ease with which the algorithm and training data used to generate the model can be determined." Access to the training data is an example of transparency.