Cyclomatic complexity would be the most effective input to an AI-based defect prediction tool.
Cyclomatic complexity is a software metric that measures the complexity of a program's control flow, which is closely related to the likelihood of defects. Higher complexity generally indicates a higher probability of defects. This makes it a strong predictor of potential issues in the code, and thus a valuable input for defect prediction.

The most appropriate metric for evaluating the similarity of data points within each group in an unsupervised learning model is intra-cluster. This metric measures how similar the data points within each cluster are to one another. The goal is to have high intra-cluster similarity, meaning the data points within a group should be similar to each other.

Sample bias occurs when the training data is not representative of the overall population that the model will encounter in practice.
In this case, the over-representation of ethnicity A (70%) compared to B, C, and D (30%) creates a sample bias, as the model may become biased towards better performance on ethnicity A.

From the confusion matrix:
True Positives (TP) = 15
False Positives (FP) = 5
False Negatives (FN) = 15
True Negatives (TN) = 65
Accuracy= (TP + TN) / Total
= (15 + 65) / 100
=80%
Precision= TP / (TP + FP)
= 15 / (15 + 5)
= 15 / 20
=75%
Section3.2 - Functional Performance Criteriain the syllabus explains accuracy and precision exactly these ways when evaluating ML classification performance.
Option B is therefore the only correct pair of values.

Unexpected changes in system behavior can occur due to the complexity of AI-based systems.
These systems often involve many interacting components, which can lead to unpredictable results or variations in performance, making it difficult to anticipate how the system will behave under certain conditions. This presents a significant challenge in testing, as such behavior can be difficult to reproduce or control.