MLS-C01 Practice Test 46 — 15 Questions

Question 1

A data scientist is training a binary classifier using a large dataset with class imbalance (90% negative, 10% positive). After training a logistic regression model, the F1 score is low but accuracy is high. Which TWO actions should the data scientist take to improve model performance? (Choose 2.)

Choose an answer to begin — your selection is scored in the full session.

Accepted Answer

Switch to evaluation metrics such as F1 score or AUC-ROC instead of accuracy.. (switch to evaluation metrics like F1 or AUC-ROC) is correct because accuracy is misleading for imbalanced datasets. Option D (resample using SMOTE) is correct because it balances the classes and helps the model learn the minority class better. Option B (feature scaling) is a general preprocessing step but does not directly address class imbalance. Option C (add more features) may not help if the model is already biased toward the majority class. Option E (increase regularization) might reduce overfitting but does not target the imbalance issue.

Answer

Apply feature scaling to ensure all features contribute equally.

Answer

Add more features to the model to improve its capacity.

Answer

Increase the regularization parameter to reduce overfitting.

Question 2

A data scientist is using Amazon SageMaker Studio notebooks for EDA. They want to share a reproducible report that includes code, visualizations, and narrative text with their team. Which approach should they use?

Accepted Answer

Save the notebook as an .ipynb file and share it via Amazon S3.. A Jupyter notebook (.ipynb) saved in SageMaker Studio contains code, visualizations, and narrative text, and sharing it via Amazon S3 allows team members to reproduce and interact with the analysis. Option B (SageMaker Clarify) is for bias detection and model explainability, not for sharing EDA reports. Option C (Amazon QuickSight) is used for interactive dashboards and does not include the underlying code. Option D (SageMaker Autopilot) automates model building and does not generate a shareable EDA report.

Answer

Use Amazon SageMaker Clarify to generate an EDA report.

Answer

Export the results to Amazon QuickSight and create a dashboard.

Answer

Use Amazon SageMaker Autopilot to generate a report.

Question 3

Which TWO of the following are best practices for exploratory data analysis when using Amazon SageMaker Data Wrangler? (Select TWO.)

Accepted Answer

Use Data Wrangler's built-in data visualizations to explore feature distributions and relationships.. Data Wrangler's built-in visualizations allow for quick exploration of feature distributions and relationships without leaving the tool, making it a best practice for EDA. Exporting the Data Wrangler flow as a Jupyter notebook enables reproducibility and sharing with the team. Storing intermediate results in Athena (A) is not a best practice specific to Data Wrangler; it adds overhead. Using EMR for data profiling (C) is unnecessary since Data Wrangler includes profiling capabilities. Exporting data to QuickSight before transformation (D) is not recommended; analysis should be done within Data Wrangler's transformation steps.

Answer

Store all intermediate results in Amazon Athena for querying.

Answer

Use Amazon EMR to run Spark jobs for data profiling.

Answer

Always export the data to Amazon QuickSight for analysis before transformation.

Question 4

A data scientist is exploring a dataset and wants to identify outliers in a numerical feature. The feature is not normally distributed. Which technique is robust to non-normal distributions?

Accepted Answer

Use the IQR method: flag values below Q1 - 1.5*IQR or above Q3 + 1.5*IQR.. The IQR method, because it does not assume a normal distribution and uses quartiles to identify outliers. Option A (MAD) is robust but compares deviations from the median; however, the IQR method is more commonly used for non-normal data. Option C (Z-score) assumes normality. Option D (flagging values more than 3 standard deviations from the mean) also assumes normality.

Answer

Compute the Median Absolute Deviation (MAD) and flag values with MAD > 3.

Answer

Calculate the Z-score and flag values with |Z| > 3.

Answer

Flag values more than 3 standard deviations from the mean.

Question 5

Which THREE of the following are valid techniques for detecting outliers in a dataset during exploratory data analysis? (Select THREE.)

Accepted Answer

Z-score method: flag points with absolute Z-score > 3.. Z-score, IQR, and Isolation Forest are all common outlier detection methods. Option B (Linear regression) is not for outlier detection; it models relationships between variables. Option D (K-means) is a clustering algorithm, not primarily for outlier detection.

Answer

Linear regression residuals.

Answer

K-means clustering.

Question 6

A machine learning team is using Amazon SageMaker Experiments to track multiple training runs. They need to compare the performance of different models based on metrics like accuracy and F1 score. However, when they view the experiment list in SageMaker Studio, the metrics are not displayed. What is the MOST likely cause?

Accepted Answer

The training script did not use the SageMaker SDK to log the metrics.. SageMaker Experiments automatically tracks parameters and metrics only when the training script explicitly logs them using the SageMaker SDK's `log_metric` function or the `sagemaker.experiments.run.Run` class. Without these SDK calls, the metrics are never recorded in the experiment's trial components, so they will not appear in the Studio experiment list. The team must instrument their training code to emit metrics for Experiments to capture them.

Answer

The training job did not define metric definitions in the algorithm specification.

Answer

The training job is running on an instance type that does not support Experiments.

Answer

The IAM role used by SageMaker does not have permission to write to the Experiments table.

Question 7

The exhibit shows a data quality report for a column named 'age'. Which potential data issue should be investigated further?

Accepted Answer

The minimum age of 0 and maximum age of 120 may be outliers. A minimum age of 0 and maximum age of 120 are potential data entry errors or outliers that warrant further investigation, as extreme values can skew analysis. Option A is incorrect because the mean and median being close suggests the distribution is relatively symmetric and not a data quality issue. Option C is incorrect because a missing value rate of 2.3% is generally considered low and may be handled without major concern. Option D is incorrect because 85 unique values for age is reasonable given the possible age range; it does not indicate a problem.

Answer

The mean and median are significantly different

Answer

The missing value rate of 2.3% is too high

Answer

The number of unique values (85) is too high

Question 8

A data scientist wants to understand the distribution of a continuous feature before training a model. Which visualization is most appropriate?

Accepted Answer

Histogram. A histogram is the standard tool for showing the distribution of a single continuous variable. Option A is wrong because scatter plots compare two variables. Option B is wrong because box plots show summary statistics, not the full distribution shape. Option D is wrong because bar charts are for categorical data.

Answer

Scatter plot

Answer

Box plot

Answer

Bar chart

Question 9

A data scientist uses Amazon QuickSight to visualize a dataset and observes that a numerical feature has a skewness of 2.5 and a kurtosis of 8. Which transformation should they apply to make the distribution more normal?

Accepted Answer

Apply a log transformation.. Apply a log transformation. A skewness of 2.5 indicates a strong right skew (positive skew), and a kurtosis of 8 indicates heavy tails (leptokurtic). Log transformation is effective in reducing right skewness and making the distribution more symmetric, which is a common step toward normality. Option A (Z-score normalization) standardizes the data but does not change the shape of the distribution. Option B (Box-Cox with lambda=0.5) is a square root transformation, which is less effective than log for high skewness; Box-Cox typically requires choosing an optimal lambda, and lambda=0 would be a log transform. Option C (Min-Max scaling) rescales the range but does not affect skewness or kurtosis.

Answer

Standardize the feature using Z-score normalization.

Answer

Apply a Box-Cox transformation with lambda=0.5.

Answer

Apply Min-Max scaling to the range [0,1].

Question 10

A data scientist is performing feature engineering on a dataset with high cardinality categorical features (e.g., ZIP codes with thousands of unique values). Which technique is most effective for reducing dimensionality while preserving predictive power?

Accepted Answer

Target encoding. Target encoding (also known as mean encoding) replaces each category with the mean of the target variable for that category. This preserves the predictive signal by directly encoding the relationship between the category and the target, while reducing the dimensionality to a single continuous feature. Hash encoding can cause collisions and loss of information. One-hot encoding creates too many dummy variables for high cardinality features. Label encoding imposes an arbitrary ordinal relationship that may not exist and can mislead models.

Answer

Hash encoding

Answer

One-hot encoding

Answer

Label encoding

Question 11

A data scientist is building a regression model to predict house prices. The dataset includes a feature 'zip_code' with 1,000 unique values. What is the best way to handle this categorical feature in the exploratory data analysis phase?

Accepted Answer

Apply target encoding using the mean house price per zip code. Target encoding (option B) is the best approach for high-cardinality categorical features like zip_code. It captures the relationship between the category and the target variable (house price) without creating an excessive number of dummy variables. One-hot encoding (option A) would create 1,000 columns, leading to high dimensionality and sparsity. Label encoding (option D) implies an ordinal relationship, which does not exist for zip codes. Frequency encoding (option C) may not capture price variation well because two zip codes with the same frequency could have very different average prices.

Answer

One-hot encode the zip_code feature

Answer

Replace zip_code with the frequency of each zip code in the dataset

Answer

Use label encoding: assign each zip code a unique integer

Question 12

Which TWO actions are appropriate during exploratory data analysis when you discover that a categorical feature has 50 unique values (high cardinality)?

Accepted Answer

Group rare categories into a single 'Other' category.. Options A and E are correct. A: Grouping rare categories into an 'Other' category reduces cardinality while preserving information, which is appropriate for high-cardinality categorical features. E: Feature hashing (hashing trick) transforms high-cardinality features into a fixed-size vector, reducing dimensionality. Option B is incorrect because one-hot encoding with 50 categories creates many sparse columns, which can be problematic for model performance and memory. Option C is incorrect because label encoding implies an ordinal relationship, which may not exist, and can mislead models. Option D is incorrect because dropping the feature may lose important information; other techniques like grouping or hashing are preferable.

Answer

Apply one-hot encoding to create 50 dummy variables.

Answer

Apply label encoding to assign integers to each category.

Answer

Drop the feature entirely.

Question 13

Refer to the exhibit. The log shows the end of a successful SageMaker training job. However, the ML engineer cannot find the model artifacts in the specified S3 bucket. What is the most likely cause?

Accepted Answer

The IAM role used by the training job does not have permission to write to the S3 bucket.. The training job completed successfully, meaning the SageMaker training container executed without errors. However, if the model artifacts are not found in the specified S3 bucket, the most likely cause is that the IAM role associated with the training job lacks the necessary s3:PutObject permission for that bucket. SageMaker uses the role's credentials to write the output; without write access, the artifacts are silently dropped or fail to upload, even though the training code itself may have run to completion.

Answer

The S3 bucket does not exist.

Answer

The model artifacts were uploaded to a different S3 path.

Answer

The training job did not have network access to S3.

Question 14

A retail company uses Amazon SageMaker to train a model for product demand forecasting. The dataset contains daily sales data for 10,000 products over 3 years. The data includes features like price, promotions, holidays, and seasonality. The data scientist uses a linear regression model and gets an RMSE of 50 units. However, the business requires more accurate forecasts, especially for products with high variability. The scientist notices that the residuals show a pattern: the model underestimates demand during promotional periods. Which approach should the scientist take to improve the model?

Accepted Answer

Add interaction features between promotion and other variables.. Adding interaction features between promotion and other variables allows the model to capture the specific effect of promotions on demand, which the linear regression currently underestimates. Option B (more data) may help but won't directly address the structural bias; Option C (LSTM) might be overkill and not directly solve the underestimation during promotions; Option D (removing promotion features) would worsen the problem by discarding valuable information.

Answer

Collect more historical data for training.

Answer

Use a deep learning model like LSTM.

Answer

Remove promotion features to simplify the model.

Question 15

A startup is using SageMaker to train a model using the built-in XGBoost algorithm. The training job runs successfully but the resulting model performs poorly on the test data. The data scientist suspects overfitting. The training data is relatively small (10,000 rows). Which action should be taken to reduce overfitting?

Accepted Answer

Decrease the number of trees (num_round) to 50. Overfitting occurs when the model learns noise in the training data. Decreasing the number of trees (num_round) reduces model complexity, which helps prevent overfitting, especially with a small dataset (10,000 rows). Option B (increasing learning rate) can cause the model to converge too quickly to a suboptimal solution, potentially increasing overfitting. Option C (increasing trees) increases complexity and overfitting. Option D (larger instance) does not affect overfitting as it only changes compute resources.

Answer

Increase the learning rate to 0.3

Answer

Increase the number of trees (num_round) to 500

Answer

Use a larger instance type