Snowflake DSA-C03: SnowPro Advanced: Data Scientist

Last checked October 22, 2026 against the official Snowflake exam page.

1. Question 1Machine Learning Methods

   A business wants to predict whether a customer will churn next month, using labeled historical records. Which machine learning task fits?

   1. ABinary classification
   2. BTime series forecasting of revenue only
   3. CClustering with no labels
   4. DAnomaly detection with no target
   Show answer and explanationHide answer

   Correct answer: A

   Predicting a yes or no outcome from labeled history is binary classification. Clustering ignores labels, revenue forecasting predicts a value over time, and anomaly detection does not use the churn label.

2. Question 2Snowflake Platform for Data Science

   Which two statements about Snowflake micro-partitions are accurate? (Choose two.)

   1. AMicro-partitions are only available in external tables
   2. BMicro-partitions prevent any query pruning
   3. CMicro-partitions are stored with metadata that enables pruning
   4. DData is automatically organized into micro-partitions as it is loaded
   5. EMicro-partitions must be managed manually by the user for all tables
   Show answer and explanationHide answer

   Correct answer: C, D

   Metadata on micro-partitions enables pruning, and loading organizes data automatically. Users do not manage them manually, they apply to native tables, and they enable rather than prevent pruning.

3. Question 3Model Lifecycle and Operations

   Which two steps are typically part of a feature engineering pipeline? (Choose two.)

   1. ACreating and validating derived features
   2. BPrinting the feature names on paper
   3. CChanging the table's comment color
   4. DDeleting the source data after each run
   5. ECleaning and transforming raw data
   Show answer and explanationHide answer

   Correct answer: A, E

   Cleaning, transforming and validating derived features form the core of feature engineering. Printing names, color changes and deleting source data are not pipeline steps.

4. Question 4Data Governance and Sharing

   A data scientist in another account needs read access to a curated feature table without copying the data. Which Snowflake feature fits?

   1. ACreating a public web page with the data
   2. BGiving the other account the owner role
   3. CExporting the table to CSV files in email
   4. DSecure data sharing
   Show answer and explanationHide answer

   Correct answer: D

   Secure data sharing exposes data to another account without copying it, and access can be limited. Email exports, public pages and owner roles create copies or excessive access.

5. Question 5Snowflake Data Science Functions

   A data scientist needs to compute a rolling seven-day average of sales per store in SQL. Which construct is appropriate?

   1. AA GROUP BY across the full date column with no ordering or frame
   2. BA window function with partitioning by store and an ordered range of seven days
   3. CA cross join pairing each store with each calendar date before aggregating
   4. DA DISTINCT on the sales amount column to remove duplicate sale values
   Show answer and explanationHide answer

   Correct answer: B

   Window functions with partitions and ordered ranges compute rolling averages per group. GROUP BY collapses rows, cross joins explode data, and DISTINCT does not compute averages.