True or false: One must make sure that there are no outlier values in the data set before running the k-Means clustering model.

• A. False
• B. Not necessary
• C. True
• D. Not applicable

Answer: (C)

Outliers matter because k-Means uses the mean to define cluster centers and relies on minimizing squared distances. A single extreme value can pull a centroid toward itself, shifting centers and warping assignments for many points. That sensitivity makes it important to address outliers during preprocessing. Detect outliers with simple rules (like IQR or z-scores), consider transforming data, or remove the extreme cases before running k-Means. By handling outliers first, you’re more likely to obtain meaningful, representative clusters. If outliers are left in, the clustering results can be distorted, which is why this statement is considered true.