This is a critical stage where the model is evaluated to detect any biases in the data it was trained on. It directly addresses potential data biases in the model.

The syllabus explicitly mentions challenges of handling personal data and ensuring privacy when testing AI-based systems:
"The management of personal data and sensitive data is often a concern during testing, as testing typically requires realistic data and it is difficult to fully anonymize data."

AI-generated test cases are often created using machine learning (ML) models or heuristic algorithms. While these can be effective in generating large numbers of test cases quickly, they often suffer from the "test oracle problem." Test Oracle Problem: A test oracle is the mechanism used to determine the expected output of a test case. AI-generated test cases often lack expected results because AI-based tools do not inherently understand what the correct output should be.
Difficulty in Verification: Without expected results, verifying test cases becomes challenging.
Testers must rely on heuristics, anomaly detection, or significant failures, rather than traditional pass/fail conditions.

Incorrect weights refer to parameters within a trained model and are not typically considered a data quality issue. Data quality issues usually arise from the input data itself, such as security issues, hardware issues, or faulty sensors, which can lead to incorrect or missing data. Incorrect weights are a problem during the model training or fine-tuning phase, not directly related to data quality.

Metamorphic Testing (MT) is a testing technique that verifies AI-based systems by generating follow-up 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.
Metamorphic testing works by transforming source test cases into follow-up test cases Here, the source test case involves testing the medium-speed vehicle's 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.