MLA-C01 Practice Question: A data engineer is preparing a dataset for a…

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

• ✗

  All features will contribute equally

  Why it's wrong here

  Features with larger numeric ranges produce larger squared differences, so income ($20k-$200k) dominates the Euclidean distance and skews centroid assignment. It is tempting to assume k-means treats all features equally, but without normalisation the algorithm weights whichever feature has the widest raw scale most heavily.

• ✓

  Income

  Why this is correct

  Euclidean distance sums squared differences, so the feature with the widest numeric range contributes most. Income spans roughly $180k against age's 82 and purchases' 50, making its squared deviations dominate the distance metric and skew cluster assignment.

• ✗

  Number of purchases

  Why it's wrong here

  Purchases span 0–50, so its contribution to Euclidean distance is far smaller than income's 20,000–200,000 range. It is tempting because purchases are numeric and unscaled, but that suits a dataset where all features share comparable magnitudes, not this one.

• ✗

  Age

  Why it's wrong here

  Age spans 18–100, giving a range of roughly 82, dwarfed by income's 180,000 spread, so it cannot dominate squared distances. It is tempting because age is unscaled, but that suits features with similar ranges, not this mix.

Go deeper

Related to this question