Getting CT-AI certification is an important step in your career, but preparing for it can feel challenging. At skillcertexams, we know that having the right resources and support is essential for success. That’s why we created a platform with everything you need to prepare for CT-AI and reach your certification goals with confidence.
Your Journey to Passing the ISTQB Certified Tester AI Testing Exam CT-AI Exam
Whether this is your first step toward earning the ISTQB Certified Tester AI Testing Exam CT-AI certification, or you're returning for another round, we’re here to help you succeed. We hope this exam challenges you, educates you, and equips you with the knowledge to pass with confidence. If this is your first study guide, take a deep breath—this could be the beginning of a rewarding career with great opportunities. If you’re already experienced, consider taking a moment to share your insights with newcomers. After all, it's the strength of our community that enhances our learning and makes this journey even more valuable.
Why Choose SkillCertExams for CT-AI Certification?
Expert-Crafted Practice Tests
Our practice tests are designed by experts to reflect the actual CT-AI practice questions. We cover a wide range of topics and exam formats to give you the best possible preparation. With realistic, timed tests, you can simulate the real exam environment and improve your time management skills.
Up-to-Date Study Materials
The world of certifications is constantly evolving, which is why we regularly update our study materials to match the latest exam trends and objectives. Our resources cover all the essential topics you’ll need to know, ensuring you’re well-prepared for the exam's current format.
Comprehensive Performance Analytics
Our platform not only helps you practice but also tracks your performance in real-time. By analyzing your strengths and areas for improvement, you’ll be able to focus your efforts on what matters most. This data-driven approach increases your chances of passing the CT-AI practice exam on your first try.
Learn Anytime, Anywhere
Flexibility is key when it comes to exam preparation. Whether you're at home, on the go, or taking a break at work, you can access our platform from any device. Study whenever it suits your schedule, without any hassle. We believe in making your learning process as convenient as possible.
Trusted by Thousands of Professionals
Over 10000+ professionals worldwide trust skillcertexams for their certification preparation. Our platform and study material has helped countless candidates successfully pass their CT-AI exam questions, and we’re confident it will help you too.
What You Get with SkillCertExams for CT-AI
Realistic Practice Exams: Our practice tests are designed to the real CT-AI exam. With a variety of practice questions, you can assess your readiness and focus on key areas to improve.
Study Guides and Resources: In-depth study materials that cover every exam objective, keeping you on track to succeed.
Progress Tracking: Monitor your improvement with our tracking system that helps you identify weak areas and tailor your study plan.
Expert Support: Have questions or need clarification? Our team of experts is available to guide you every step of the way.
Achieve Your CT-AI Certification with Confidence
Certification isn’t just about passing an exam; it’s about building a solid foundation for your career. skillcertexams provides the resources, tools, and support to ensure that you’re fully prepared and confident on exam day. Our study material help you unlock new career opportunities and enhance your skillset with the CT-AI certification.
Ready to take the next step in your career? Start preparing for the ISTQB CT-AI exam and practice your questions with SkillCertExams today, and join the ranks of successful certified professionals!
ISTQB CT-AI Sample Questions
Question # 1
You have access to the training data that was used to train an AI-based system. You can review thisinformation and use it as a guideline when creating your tests. What type of characteristic is this?
A. Autonomy B. Explorability C. Transparency D. Accessibility
Answer: C
Explanation:
AI-based systems can sometimes behave like black boxes, where the internal decision-making
process is unclear. Transparency refers to the ability to inspect and understand the training data,
algorithms, and decision-making process of the AI system.
Why is Option C Correct?
Transparency ensures that testers and stakeholders can review how an AI system was trained.
Access to training data is a key factor in transparency because it allows testers to analyze biases,
completeness, and representativeness of the dataset.
Transparency is an essential characteristic of explainable AI (XAI).
Having access to training data means that testers can investigate how data influences AI behavior.
Regulatory and ethical AI guidelines emphasize transparency.
Many AI ethics frameworks, such as GDPR and Trustworthy AI guidelines, recommend transparency
to ensure fair and explainable AI decision-making.
Why Other Options are Incorrect?
(A) Autonomy ⠌
Autonomy refers to an AI systems ability to make decisions independently without human
intervention. However, having access to training data does not relate to autonomy, which is more
about self-learning and decision-making without human control.
(B) Explorability ⠌
Explorability refers to the ability to test AI systems interactively to understand their behavior, but it
does not directly relate to accessing training data.
(D) Accessibility ⠌
Accessibility refers to the ease with which people can use the system, not the ability to inspect the
training data.
Reference from ISTQB Certified Tester AI Testing Study Guide
Transparency is the ease with which the training data and algorithm used to generate a model can be understood.
"Transparency: This is considered to be the ease with which the algorithm and training data used to generate the model can be determined."
Thus, option C is the correct answer, as transparency involves access to training data, allowing testers to understand AI decision-making processes.
Question # 2
A transportation company operates three types of delivery vehicles in its fleet. The vehicles operateat different speeds (slow, medium, and fast). The transportation company is attempting to optimizescheduling and has created an AI-based program to plan routes for its vehicles using records from themedium-speed vehicle traveling to selected destinations. The test team uses this data inmetamorphic testing to test the accuracy of the estimated travel times created by the AI routeplanner with the actual routes and times.Which of the following describes the next phase of metamorphic testing?
A. The team tests the time required for the fast and slow vehicles to travel the same route as themedium vehicle. Then, by calculating the speed difference, they then predict how much faster orslower the vehicles will travel. That information is then used to verify that the arrival time of thevehicles meets the expected result. B. The team decomposes each route into the relevant components that affect the travel time such astraffic density and vehicle power. The team then uses statistical analysis to characterize the influenceof each component to calculate the fast and slow vehicle route times. C. The team uses an AI system to select the most dissimilar routes. With this information, any of theAI routes can be metaphorically transformed into a fast or slow route. D. The team uses the same AI route planner to create routes that are longer and shorter but followthe same track. Finally, by driving the fast vehicles on the long routes and slow vehicles on the shortroutes and vice versa, the AI system will have enough information to infer travel times for all vehicleson all routes.
Answer: A
Explanation:
Metamorphic Testing (MT) is a testing technique that verifies AI-based systems by generating followup
test cases based on existing test cases. These follow-up test cases adhere to a Metamorphic
Relation (MR), ensuring that if the system is functioning correctly, changes in input should result in
predictable changes in output.
Why Option A is Correct?
Metamorphic testing works by transforming source test cases into follow-up test cases
Here, the source test case involves testing the medium-speed vehicles travel time.
The follow-up test cases are derived by extrapolating travel times for fast and slow vehicles using
predictable relationships based on speed differences.
MR states that modifying input should result in a predictable change in output
Since the speed of the vehicle is a known factor, it is possible to predict the new arrival times and
verify whether they follow expected trends.
This is a direct application of metamorphic testing principles
In route optimization systems, metamorphic testing often applies transformations to speed, distance,
or conditions to verify expected outcomes.
Why Other Options are Incorrect?
(B) Decomposing each route into traffic density and vehicle power ⠌
While useful for statistical analysis, this approach does not generate follow-up test cases based on a
defined metamorphic relation (MR).
(C) Selecting dissimilar routes and transforming them into a fast or slow route ⠌
This does not follow metamorphic testing principles, which require predictable transformations.
(D) Running fast vehicles on long routes and slow vehicles on short routes ⠌
This method does not maintain a controlled MR and introduces too many uncontrolled variables.
Reference from ISTQB Certified Tester AI Testing Study Guide
Metamorphic testing generates follow-up test cases based on a source test case.
"MT is a technique aimed at generating test cases which are based on a source test case that has
passed. One or more follow-up test cases are generated by changing (metamorphizing) the source
test case based on a metamorphic relation (MR)."
MT has been used for testing route optimization AI systems.
"In the area of AI, MT has been used for testing image recognition, search engines, route
optimization and voice recognition, among others."
Thus, option A is the correct answer, as it aligns with the principles of metamorphic testing by
modifying input speeds and verifying expected results.
Question # 3
A mobile app start-up company is implementing an AI-based chat assistant for e-commercecustomers. In the process of planning the testing, the team realizes that the specifications areinsufficient.Which testing approach should be used to test this system?
A. Exploratory testing B. Static analysis C. Equivalence partitioning D. State transition testing
Answer: A
Explanation:
When testing an AI-based chat assistant for e-commerce customers, the lack of sufficient
specifications makes it difficult to use structured test techniques. The ISTQB CT-AI Syllabus
recommends exploratory testing in such cases:
Why Exploratory Testing?
Exploratory testing is useful when specifications are incomplete or unclear.
AI-based systems, particularly those using natural language processing (NLP), may not behave
deterministically, making scripted test cases ineffective.
The tester interacts dynamically with the system, identifying unexpected behaviors not documented
in the specification .
Analysis of Answer Choices:
A (Exploratory testing) → Correct, as it is the best approach when specifications are incomplete.
B (Static analysis) → Incorrect, as static analysis checks code without execution, which is not helpful
for AI chatbots.
C (Equivalence partitioning) → Incorrect, as this technique requires well-defined inputs and outputs,
which are missing due to insufficient specifications.
D (State transition testing) → Incorrect, as state-based testing requires knowledge of valid and invalid
transitions, which is difficult with a chatbot lacking a clear specification .
Thus, Option A is the correct answer, as exploratory testing is the best approach when dealing with
insufficient specifications in AI-based systems.
Certified Tester AI Testing Study Guide Reference:
ISTQB CT-AI Syllabus v1.0, Section 7.7 (Selecting a Test Approach for an ML System)
Which of the following is correct regarding the layers of a deep neural network?
A. There is only an input and output layer B. There is at least one internal hidden layer C. There must be a minimum of five total layers to be considered deep D. The output layer is not connected with the other layers to maintain integrity
Answer: B
Explanation:
A deep neural network (DNN) is a type of artificial neural network that consists of multiple layers
between the input and output layers. The ISTQB Certified Tester AI Testing (CT-AI) Syllabus outlines
the following characteristics of a DNN:
Structure of a Deep Neural Network:
A DNN comprises at least three types of layers:
Input layer: Receives the input data.
Hidden layers: Perform complex feature extraction and transformations.
Output layer: Produces the final prediction or classification .
Analysis of Answer Choices:
A (Only input and output layers) → Incorrect, as a DNN must have at least one hidden layer.
B (At least one internal hidden layer) → Correct, as a neural network must have hidden layers to be
considered deep.
C (Minimum of five layers required) → Incorrect, as there is no strict definition that requires at least
five layers.
D (Output layer is not connected to other layers) → Incorrect, as the output layer must be connected
to the hidden layers .
Thus, Option B is the correct answer, as a deep neural network must have at least one hidden layer.
Certified Tester AI Testing Study Guide Reference:
ISTQB CT-AI Syllabus v1.0, Section 6.1 (Neural Networks and Deep Neural Networks)
ISTQB CT-AI Syllabus v1.0, Section 6.2 (Structure of Deep Neural Networks) .
Question # 5
When verifying that an autonomous AI-based system is acting appropriately, which of the followingare MOST important to include?
A. Test cases to verify that the system automatically confirms the correct classification of trainingdata B. Test cases to detect the system appropriately automating its data input C. Test cases to detect the system prompting for unnecessary human intervention D. Test cases to verify that the system automatically suppresses invalid output data
Answer: C
Explanation:
When verifying autonomous AI-based systems, a critical aspect is ensuring that they maintain an
appropriate level of autonomy while only requesting human intervention when necessary. If an AI
system unnecessarily asks for human input, it defeats the purpose of autonomy and can:
Slow down operations.
Reduce trust in the system.
Indicate improper confidence thresholds in decision-making.
This is particularly crucial in autonomous vehicles, AI-driven financial trading, and robotic process
automation, where excessive human intervention would hinder performance.
Why are the other options incorrect?
A . Test cases to verify that the system automatically confirms the correct classification of training
data → This is relevant for verifying training consistency but not for autonomy validation.
B . Test cases to detect the system appropriately automating its data input → While relevant, data
automation does not directly address the verification of autonomy.
D . Test cases to verify that the system automatically suppresses invalid output data → This focuses
on output filtering rather than decision-making autonomy.
Thus, the most critical test case for verifying autonomous AI-based systems is ensuring that it does
not unnecessarily request human intervention.
Reference from ISTQB Certified Tester AI Testing Study Guide:
Section: Section 8.2 - Testing Autonomous AI-Based Systems states that it is crucial to test whether the system
requests human intervention only when necessary and does not disrupt autonomy .
Question # 6
A beer company is trying to understand how much recognition its logo has in the market. It plans todo that by monitoring images on various social media platforms using a pre-trained neural networkfor logo detection. This particular model has been trained by looking for words, as well as matchingcolors on social media images. The company logo has a big word across the middle with a bold blueand magenta border.Which associated risk is most likely to occur when using this pre-trained model?
A. There is no risk, as the model has already been trained B. Insufficient function; the model was not trained to check for colors or words C. Improper data preparation D. Inherited bias: the model could have inherited unknown defects
Answer: D
Explanation:
A major risk when using a pre-trained neural network for logo detection is that it may inherit biases
and defects from the original dataset and training process. This means that the model could
misidentify or fail to recognize certain logos due to:
Differences in data preparation: The original training data may have used a different preprocessing
method than the new dataset, leading to inconsistencies.
Limited transparency: The exact details of the dataset and biases within it may not be known, which
can cause unexpected behavior.
Bias in logo detection: If the model was trained on a dataset with certain color or text preferences, it
may disproportionately misidentify logos with similar characteristics.
This inherited bias can result in:
False Positives: Recognizing other brand logos as the beer company's logo.
False Negatives: Failing to detect the actual logo when variations occur (e.g., different lighting or
partial visibility).
Algorithmic Bias: The model may favor certain shapes or color contrasts due to biased training data.
Thus, the most appropriate risk associated with using this pre-trained model is inherited bias.
Reference from ISTQB Certified Tester AI Testing Study Guide:
Section: Section 1.8.3 - Risks of Using Pre-Trained Models and Transfer Learning explains how pre-trained
models may inherit biases and undocumented defects that affect performance in a new
environment .
Question # 7
A local business has a mail pickup/delivery robot for their office. The robot currently uses a track tomove between pickup/drop off locations. When it arrives at a destination, the robot stops to allow ahuman to remove or deposit mail.The office has decided to upgrade the robot to include AI capabilities that allow the robot to performits duties without a track, without running into obstacles, and without human intervention.The test team is creating a list of new and previously established test objectives and acceptancecriteria to be used in the testing of the robot upgrade. Which of the following test objectives will testan AI quality characteristic for this system?
A. The robot must evolve to optimize its routing B. The robot must recharge for no more than six hours a day C. The robot must record the time of each delivery which is compiled into a report D. The robot must complete 99.99% of its deliveries each day
Answer: A
Explanation:
AI-based systems have specific quality characteristics, including evolution, autonomy, and
adaptability. A test objective that evaluates whether an AI system evolves to improve performance
over time directly aligns with AI quality characteristics .
Explanation of Answer Choices:
Option A: The robot must evolve to optimize its routing.
Correct. Evolution is an AI quality characteristic that ensures the system learns from past experiences
and adapts to improve efficiency .
Option B: The robot must recharge for no more than six hours a day.
Incorrect. This is an operational constraint rather than an AI-specific quality characteristic .
Option C: The robot must record the time of each delivery which is compiled into a report.
Incorrect. Logging data does not relate to AI quality characteristics like adaptability or autonomy .
Option D: The robot must complete 99.99% of its deliveries each day.
Incorrect. This is a performance target rather than an AI quality characteristic .
ISTQB CT-AI Syllabus Reference:
Evolution as an AI Quality Characteristic: "Check how well the system learns from its own experience.
Check how well the system copes when the profile of data changes (i.e., concept drift)" .
Thus, Option A is the best choice as it directly tests an AI quality characteristic (evolution) in the
upgraded autonomous robot.
Question # 8
Which of the following is a dataset issue that can be resolved using pre-processing?
A. Insufficient data B. Invalid data C. Wanted outliers D. Numbers stored as strings
Answer: D
Explanation:
Pre-processing is an essential step in data preparation that ensures data is clean, formatted correctly,
and structured for effective machine learning (ML) model training. One common issue that can be
resolved during pre-processing is numbers stored as strings.
Explanation of Answer Choices:
Option A: Insufficient data
Incorrect. Pre-processing cannot resolve insufficient data. If data is lacking, techniques like data
augmentation or external data collection are needed .
Option B: Invalid data
Incorrect. While pre-processing can identify and handle some forms of invalid data (e.g., missing
values, duplicate entries), it does not resolve all invalid data issues. Some cases may require domain
expertise to determine validity .
Option C: Wanted outliers
Incorrect. Pre-processing usually focuses on handling unwanted outliers. Wanted outliers may need
to be preserved, which is more of a data selection decision rather than pre-processing .
Option D: Numbers stored as strings
Correct. One of the key functions of data pre-processing is data transformation, which includes
converting incorrectly formatted data types, such as numbers stored as strings, into their correct
numerical format .
ISTQB CT-AI Syllabus Reference:
Data Pre-Processing Steps: "Transformation: The format of the given data is changed (e.g., breaking
an address held as a string into its constituent parts, dropping a field holding a random identifier,
converting categorical data into numerical data, changing image formats)" .
Question # 9
Which of the following characteristics of AI-based systems make it more difficult to ensure they aresafe?
A. Simplicity B. Sustainability C. Non-determinism D. Robustness
Answer: C
Explanation:
AI-based systems often exhibit non-deterministic behavior, meaning they do not always produce the
same output for the same input. This makes ensuring safety more difficult, as the system's behavior
can change based on new data, environmental factors, or updates .
Why Non-determinism Affects Safety:
In traditional software, the same input always produces the same output.
In AI systems, outputs vary probabilistically depending on learned patterns and weights.
This unpredictability makes it harder to verify correctness, reliability, and safety, especially in critical
domains like autonomous vehicles, medical AI, and industrial automation.
Why Other Options Are Incorrect:
A (Simplicity): AI-based systems are typically complex, not simple, which contributes to safety
challenges .
B (Sustainability): While sustainability is an important AI consideration, it does not directly affect
safety .
D (Robustness): Lack of robustness can make AI systems unsafe, but non-determinism is the primary
issue that complicates safety verification .
Supporting Reference from ISTQB Certified Tester AI Testing Study Guide:
ISTQB CT-AI Syllabus (Section 2.8: Safety and AI)
"The characteristics of AI-based systems that make it more difficult to ensure they are safe include:
complexity, non-determinism, probabilistic nature, self-learning, lack of transparency,
interpretability and explainability, lack of robustness" .
Conclusion:
Since non-determinism makes AI behavior unpredictable, complicating safety assurance, the correct
answer is C.
Question # 10
Which of the following is a technique used in machine learning?
A. Decision trees B. Equivalence partitioning C. Boundary value analysis D. Decision tables
Answer: A
Explanation:
Decision trees are a widely used machine learning (ML) technique that falls under supervised
learning. They are used for both classification and regression tasks and are popular due to their
interpretability and effectiveness.
How Decision Trees Work:
The model splits the dataset into branches based on feature conditions.
It continues to divide the data until each subset belongs to a single category (classification) or
predicts a continuous value (regression).
The final result is a tree structure where decisions are made at nodes, and predictions are given at
leaf nodes.
Common Applications of Decision Trees:
Fraud detection
Medical diagnosis
Customer segmentation
Recommendation systems
Why Other Options Are Incorrect:
B (Equivalence Partitioning): This is a software testing technique, not a machine learning method. It
is used to divide input data into partitions to reduce test cases while maintaining coverage .
C (Boundary Value Analysis): Another software testing technique, used to check edge cases around
input boundaries .
D (Decision Tables): A structured testing technique used to validate business rules and logic, not a
machine learning method .
Supporting Reference from ISTQB Certified Tester AI Testing Study Guide:
ISTQB CT-AI Syllabus (Section 3.1: Forms of Machine Learning - Decision Trees)
"Decision trees are used in classification and regression models and are fundamental ML algorithms" .
Conclusion:
Since decision trees are a core technique in machine learning, while the other options are software
testing techniques, the correct answer is A.
Question # 11
Which of the following aspects is a challenge when handling test data for an AI-based system?
A. Personal data or confidential data B. Output data or intermediate data C. Video frame speed or aspect ratio D. Data frameworks or machine learning frameworks
Answer: A
Explanation:
Handling test data in AI-based systems presents numerous challenges, particularly in terms of data
privacy and confidentiality. AI models often require vast amounts of training data, some of which
may contain personal, sensitive, or confidential information. Ensuring compliance with data
protection laws (e.g., GDPR, CCPA) and implementing secure data-handling practices is a major
challenge in AI testing.
Why is Option A Correct?
Data Privacy Regulations
AI-based systems frequently process personal data, such as images, names, and transaction details,
leading to privacy concerns.
Compliance with regulations such as GDPR (General Data Protection Regulation) and CCPA (California
Consumer Privacy Act) requires proper anonymization, encryption, or redaction of sensitive data
before using it for testing.
Data Security Challenges
AI models may leak confidential information if proper security measures are not in place.
Protecting training and test data from unauthorized access is crucial to maintaining trust and
compliance.
Legal and Ethical Considerations
Organizations must obtain legal approval before using certain datasets, especially those containing
health records, financial data, or personally identifiable information (PII).
Testers may need to employ synthetic data or data masking techniques to minimize exposure risks.
Why Other Options are Incorrect?
(B) Output data or intermediate data ⠌
While analyzing output data is important, it does not pose a significant challenge compared to
handling personal or confidential test data.
(C) Video frame speed or aspect ratio ⠌
These are technical challenges in processing AI models but do not fall under data privacy or ethical
considerations.
(D) Data frameworks or machine learning frameworks ⠌
Choosing an appropriate ML framework (e.g., TensorFlow, PyTorch) is important, but it is not a major
challenge related to test data handling.
Reference from ISTQB Certified Tester AI Testing Study Guide
Handling personal or confidential data is a critical challenge in AI testing
"Personal or otherwise confidential data may need special techniques for sanitization, encryption, or
redaction. Legal approval for use may also be required."
Thus, option A is the correct answer, as data privacy and confidentiality are major challenges when
handling test data for AI-based systems.
Question # 12
A neural network has been designed and created to assist day-traders improve efficiency whenbuying and selling commodities in a rapidly changing market. Suppose the test team executes a teston the neural network where each neuron is examined. For this network the shortest path indicates abuy, and it will only occur when the one-day predicted value of the commodity is greater than thespot price by 0.75%. The neurons are stimulated by entering commodity prices and testers verify thatthey activate only when the future value exceeds the spot price by at least 0.75%.Which of the following statements BEST explains the type of coverage being tested on the neuralnetwork?
A. Threshold coverage B. Neuron coverage C. Sign-change coverage D. Value-change coverage
Answer: A
Explanation:
Threshold coverage is a specific type of coverage measure used in neural network testing. It ensures
that each neuron in the network achieves an activation value greater than a specified threshold. This
is particularly relevant to the scenario described, where testers verify that neurons activate only
when the future value of the commodity exceeds the spot price by at least 0.75%.
Why is Threshold Coverage Correct?
Threshold-based activation: The test case in the question is explicitly verifying whether neurons
activate only when a certain threshold (0.75%) is exceeded. This aligns perfectly with the definition
of threshold coverage.
Common in Neural Network Testing: Threshold coverage is used to measure whether each neuron in
a neural network reaches a specified activation value, ensuring that the neural network behaves as
expected when exposed to different test inputs.
Precedent in Research: The DeepXplore framework used a threshold of 0.75% to identify incorrect
behaviors in neural networks, making this coverage criterion well-documented in AI testing research.
Why Other Options are Incorrect?
(B) Neuron Coverage ⠌
Neuron coverage only checks whether a neuron activates (non-zero value) at some point during
testing. It does not consider specific activation thresholds, making it less precise for this scenario.
(C) Sign-Change Coverage ⠌
This coverage measures whether each neuron exhibits both positive and negative activation values,
which is not relevant to the given scenario (where activation only matters when exceeding a specific
threshold).
(D) Value-Change Coverage ⠌
This coverage requires each neuron to produce two activation values that differ by a chosen
threshold, but the question focuses on whether activation occurs beyond a fixed threshold, not
changes in activation values.
Reference from ISTQB Certified Tester AI Testing Study Guide
Threshold coverage ensures that neurons exceed a given activation threshold
"Full threshold coverage requires that each neuron in the neural network achieves an activation
value greater than a specified threshold. The researchers who created the DeepXplore framework
suggested neuron coverage should be measured based on an activation value exceeding a threshold,
changing based on the situation."
Thus, option A is the correct answer, as threshold coverage ensures the neural network's activation is
correctly evaluated based on the required condition (0.75%).
Question # 13
Which of the following is an example of a clustering problem that can be resolved by unsupervisedlearning?
A. Associating shoppers with their shopping tendencies B. Grouping individual fish together based on their types of fins C. Classifying muffin purchases based on the perceived attractiveness of their packaging D. Estimating the expected purchase of cat food after a particularly successful ad campaign
Answer: A
Explanation:
Clustering is a form of unsupervised learning, which groups data points based on similarities without
predefined labels. According to ISTQB CT-AI Syllabus, clustering is used in scenarios where:
The objective is to find natural groupings in data.
The dataset does not have labeled outputs.
Patterns and structures need to be identified automatically .
Analyzing the answer choices:
A . Associating shoppers with their shopping tendencies → Correct
Shoppers can be grouped based on purchasing behaviors (e.g., luxury shoppers vs. budget-conscious
shoppers), which is a typical clustering application in market segmentation.
B . Grouping individual fish together based on their types of fins → Incorrect
If the types of fins are labeled, it becomes a classification problem, which requires supervised
learning.
C . Classifying muffin purchases based on packaging attractiveness → Incorrect
Classification, not clustering, because attractiveness scores or labels must be predefined.
D . Estimating the expected purchase of cat food after an ad campaign → Incorrect
This is a prediction task, best suited for regression models, which are part of supervised learning.
Thus, Option A is the best answer, as clustering is used to group shoppers based on tendencies
without predefined labels .
Certified Tester AI Testing Study Guide Reference:
ISTQB CT-AI Syllabus v1.0, Section 3.3 (Selecting a Form of ML - Clustering) .
Question # 14
Consider a machine learning model where the model is attempting to predict if a patient is at risk forstroke. The model collects information on each patient regarding their blood pressure, red blood cellcount, smoking, status, history of heart disease, cholesterol level, and demographics. Then, using adecision tree the model predicts whether or not the associated patient is likely to have a stroke in thenear future. One the model is created using a training data set, it is used to predict a stroke in 80additional patients. The table below shows a confusion matrix on whether or not the model mode acorrect or incorrect prediction.The testers have calculated what they believe to be an appropriate functional performance metricfor the model. They calculated a value of 2 or 0.6667.
A. F1 “source B. Precision C. Recall D. Accuracy
Answer: D
Explanation:
The problem describes a classification model that predicts whether a patient is at risk for a stroke.
The confusion matrix is provided, and the testers have calculated a performance metric as 2 or
0.6667.
From the ISTQB Certified Tester AI Testing (CT-AI) Syllabus, the definitions of functional performance
Consider a natural language processing (NLP) algorithm that attempts to predict the next word thatyou would like to type in a text message. An update to the algorithm has been created that shouldincrease the accuracy of the predictions based on user typing patterns. The old algorithm was ratedfor accuracy by the users. Then, after the new update was released, the users rated the updatedalgorithm. A statistical test was used to compare between the two versions of the algorithm to seewhether or not the update should remain in place.This is an example of what type of testing?
A. Metamorphic testing B. A/B testing C. Exploratory testing D. Pairwise testing
Answer: B
Explanation:
A/B testing is a statistical testing method that compares two different versions of a system to
determine which one performs better. In this scenario, the old NLP algorithm was rated for accuracy,
and after the update, the new algorithm was also rated by users. A statistical test was performed to
compare the two versions, which is the fundamental approach of A/B testing.
A/B testing is commonly used in:
User experience testing (e.g., comparing different versions of a website).
ML model evaluation (e.g., comparing two AI-based classifiers).
Performance assessment (e.g., determining if a new recommendation algorithm is more effective).
This approach allows for data-driven decisions, ensuring that any changes to the system result in
meaningful improvements.
Reference from ISTQB Certified Tester AI Testing Study Guide:
Section: Section 9.4 - A/B Testing states that A/B testing is used to compare updates in AI-based systems to
