Lesson 2: Data Quality, Model Testing, and AI-Specific Risks

This lesson develops practical understanding of data quality, model testing, and ai-specific risks within the ISTQB Certified Tester AI Testing (CT-AI) Training. It connects core concepts with realistic testing and quality-engineering decisions.

Learners examine methods, evidence, risks, stakeholder expectations, and implementation considerations before applying the ideas in a focused activity.

Topics Covered

• Data correctness, completeness, relevance, balance, privacy, and representation
• Sampling, labeling, leakage, duplication, outliers, and distribution shifts
• Accuracy, precision, recall, F1, confusion matrices, and thresholds
• Bias, fairness, explainability, transparency, robustness, and adversarial risk
• Overfitting, underfitting, generalization, stability, and reproducibility
• Metamorphic, differential, back-to-back, and oracle-limited testing
• Risk prioritization for safety, ethics, law, business, and user impact

Practical Activity

Apply the lesson concepts to a realistic ISTQB Certified Tester AI Testing (CT-AI) scenario and document the test approach, evidence, risks, and recommended next actions.

Lesson Outcome

Learners can explain and apply data quality, model testing, and ai-specific risks using structured, risk-aware, and evidence-based testing decisions.