MLS-C01 Exploratory Data Analysis Practice Question
A data scientist is working on a project to predict customer churn. The dataset contains 50,000 rows and 20 features, including categorical variables like 'Region' (10 categories) and 'SubscriptionType' (5 categories). The target variable is binary (churn or not). During exploratory data analysis, they plot the distribution of each feature and notice that 'Region' has a highly imbalanced distribution: one region accounts for 80% of the data. Which of the following is the most appropriate next step?
Answer choices
Why each option matters
Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.
Correct answer & explanation
✓
Group rare categories into an 'Other' category.
Grouping rare categories into an 'Other' category helps manage highly imbalanced categorical features, preventing the model from overemphasizing the dominant category and allowing rare categories to be represented without causing sparse or noisy signals. Option A is incorrect: one-hot encoding does not address the imbalance; it simply creates dummy variables, and rare categories would still be underrepresented. Option B is incorrect: removing the 'Region' feature could discard potentially useful information; the problem is imbalance, not irrelevance. Option D is incorrect: oversampling the minority class targets address target imbalance, not feature imbalance.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Apply one-hot encoding to the 'Region' feature.
Why it's wrong here
One-hot encoding does not address the imbalance; it simply creates dummy variables, and rare categories would still be underrepresented.
- ✗
Remove the 'Region' feature from the dataset.
Why it's wrong here
Removing the 'Region' feature could discard potentially useful information; the problem is imbalance, not irrelevance.
- ✓
Group rare categories into an 'Other' category.
Why this is correct
Grouping rare categories into an 'Other' category helps manage highly imbalanced categorical features, preventing the model from overemphasizing the dominant category and allowing rare categories to be represented without causing sparse or noisy signals.
- ✗
Oversample the minority classes in the target variable.
Why it's wrong here
Oversampling the minority class targets addresses target imbalance, not feature imbalance.
Go deeper
Related to this question
About these practice questions
Courseiva writes every MLS-C01 question from scratch — 1,672 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or dumps. Learn why practice questions differ from exam dumps →
Same concept, more angles
1 more way this is tested on MLS-C01
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. During EDA, a data scientist finds that a categorical feature 'city' has 500 unique values but only 10 cities account for 90% of the data. What is a recommended way to handle the rare categories?
easy- ✓ A.Group rare categories into a single 'Other' category.
- B.Apply label encoding to all categories.
- C.One-hot encode all 500 categories.
- D.Drop all rows with rare categories.
Why A: Grouping rare categories into 'Other' reduces cardinality, avoids overfitting from high-dimensional sparse features, and retains the majority of data from the top 10 cities. Option B (label encoding) is not recommended as it imposes an arbitrary ordinal relationship that may mislead the model. Option C (one-hot encoding all 500 categories) would create 499 dummy features, leading to the curse of dimensionality and sparse data. Option D (dropping rows with rare categories) discards potentially valuable data and may introduce bias.
JA
Written by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
This MLS-C01 practice question is part of Courseiva's free Amazon Web Services certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the MLS-C01 exam.