Because the mean is easily influenced by ______, it is important to handle such data before generating a k-Means model.

• A. Outlier Values
• B. High Variability
• C. Missing Values
• D. Noise

Answer: (A)

The mean is used to position the centroid in k-Means, so extreme observations can pull that centroid toward themselves. When a data point is an outlier, it can distort the average of its cluster, shifting the center and causing many other points to be assigned to the wrong cluster. This is why handling outliers before running k-Means is important: you either remove or lessen the impact of those extreme values, or use a more robust clustering method that doesn’t rely on the mean as the center. While issues like high variability, missing values, or noise can affect clustering, the mean’s susceptibility to extreme values is the main reason to address outliers first.