[Mar-2026] DSA-C03 Dumps PDF – DSA-C03 Real Exam Questions Answers [Q102-Q126]

NO.102 You’ve trained a sales forecasting model using Snowpark ML and want to deploy it within Snowflake for real-time predictions. You’ve decided to store the predictions directly in a Snowflake table. The model predicts sales for different product categories based on historical data and promotional activities. Which of the following approaches is the MOST efficient and scalable way to store these predictions, considering a high volume of prediction requests and the need for quick retrieval for downstream dashboards?

Storing predictions in a single, wide table with all features and predictions as columns. No partitioning or clustering is implemented.

Storing predictions in a separate table with a composite key of product category and timestamp, with clustering on the timestamp column and partitioning by product category.

Storing predictions in a VARIANT column in a single table. All prediction results for a given product category are stored as a JSON document within the VARIANT column.

Storing predictions in an external stage (e.g., AWS S3) and querying them using an external table. The external table definition includes the sales prediction as a column.

Storing predictions in a key-value store like Redis and referencing the keys from a Snowflake table. Requires external network access from Snowflake.

NO.103 You are deploying a large language model (LLM) to Snowflake using a user-defined function (UDF). The LLM’s model file, ’11m model.pt’, is quite large (5GB). You’ve staged the file to Which of the following strategies should you employ to ensure successful deployment and efficient inference within Snowflake? Select all that apply.

Use the ‘PUT’ command with to compress the model file before staging it. Snowflake will automatically decompress it during UDF execution.

Increase the warehouse size to XLARGE or larger to provide sufficient memory for loading the large model into the UDF environment.

Leverage Snowflake’s Snowpark Container Services to deploy the LLM as a separate containerized application and expose it via a Snowpark API. Then call that endpoint from snowflake.

Use the ‘IMPORTS’ clause in the UDF definition to reference Ensure the UDF code loads the model lazily (i.e., only when it’s first needed) to minimize startup time and memory usage.

Split the large model file into smaller chunks and stage each chunk separately. Reassemble the model within the UDF code before inference.

NO.104 You are tasked with estimating the 95% confidence interval for the median annual income of Snowflake customers. Due to the non-normal distribution of incomes and a relatively small sample size (n=50), you decide to use bootstrapping. You have a Snowflake table named ‘customer_income’ with a column ‘annual_income’. Which of the following SQL code snippets, when correctly implemented within a Python script interacting with Snowflake, would most accurately achieve this using bootstrapping with 1000 resamples and properly calculate the confidence interval?

NO.105 You are building a fraud detection model in Snowflake using Snowpark Python. You want to evaluate the model’s performance, particularly focusing on identifying instances of fraud (minority class). Which combination of metrics provides the most comprehensive assessment for this imbalanced classification problem within the Snowflake environment, considering the need to minimize both false positives (legitimate transactions flagged as fraudulent) and false negatives (fraudulent transactions missed)?

Accuracy and Recall.

Precision and Fl-score.

ROC AUC and Recall.

Precision, Recall, and Fl-score.

Accuracy and ROC AUC.

NO.106 You are building a model deployment pipeline using a CI/CD system that connects to your Snowflake data warehouse from your external IDE (VS Code) and orchestrates model training and deployment. The pipeline needs to dynamically create and grant privileges on Snowflake objects (e.g., tables, views, warehouses) required for the model. Which of the following security best practices should you implement when creating and granting privileges within the pipeline?

Use the role within the pipeline script to create and grant all necessary privileges.

Create a custom role with minimal required privileges to perform only the necessary operations for the pipeline, and grant this role to a dedicated service account used by the pipeline.

Grant the ‘ SYSADMIN’ role to the service account used by the pipeline to ensure it has sufficient privileges.

Hardcode the credentials of a highly privileged user (e.g., a user with the SECURITYADMIN role) in the pipeline script for authentication.

Grant the ‘OWNERSHIP’ privilege on all objects to the service account so it can perform any operation.

NO.107 You are tasked with preparing customer data for a churn prediction model in Snowflake. You have two tables: ‘customers’ (customer_id, name, signup_date, plan_id) and ‘usage’ (customer_id, usage_date, data_used_gb). You need to create a Snowpark DataFrame that calculates the total data usage for each customer in the last 30 days and joins it with customer information. However, the ‘usage’ table contains potentially erroneous entries with negative values, which should be treated as zero. Also, some customers might not have any usage data in the last 30 days, and these customers should be included in the final result with a total data usage of 0. Which of the following Snowpark Python code snippets will correctly achieve this?

None of the above

NO.108 You are developing a model to predict customer churn using Snowflake ML. After training a Gradient Boosting model, you want to understand the relationship between ‘number_of_products’ and the churn probability. You generate a partial dependence plot (PDP) for ‘number_of_products’. The PDP shows a steep increase in churn probability as ‘number_of_products’ increases from 1 to 3, followed by a plateau. Which of the following statements are the MOST accurate interpretations of this PDP? Assume the dataset is balanced and has undergone proper preprocessing.

Customers who purchase more than 3 products are less likely to churn, suggesting higher engagement or satisfaction.

The model is perfectly calibrated, and the PDP accurately represents the true causal effect of ‘number_of_products’ on churn.

There might be a confounding variable correlated with both ‘number_of_products’ and churn, leading to a spurious relationship in the PDP.

The PDP indicates a high degree of interaction between ‘number_of_products’ and other features in the model, making the interpretation unreliable.

Increasing the number of products purchased by all customers will definitively reduce overall churn.

NO.109 You are using Snowpark for Python to build a feature engineering pipeline for a machine learning model that predicts customer churn. The data is stored in a Snowflake table called ‘CUSTOMER DATA’ , and you want to create new features based on time-series data within the table. You need to calculate the ‘Recency’ feature (days since the last transaction) and ‘Frequency’ feature (number of transactions in the last 3 months). Considering performance and best practices, which Snowpark approach would you choose?

Fetch the entire ‘CUSTOMER DATA table into a Pandas DataFrame using , then use Pandas’ time-series functions to calculate ‘Recency’ and ‘Frequency’. After feature engineering, load the Pandas DataFrame back into Snowflake.

Use Snowpark DataFrame API to perform window functions within Snowflake to calculate ‘Recency’ and ‘Frequency’ directly, leveraging Snowflake’s processing power without transferring data to the client.

Create a Python UDF using Pandas to calculate ‘Recency’ and ‘Frequency’. Apply this UDF to the ‘CUSTOMER DATA’ table through Snowpark, processing the data row by row.

Write a stored procedure in SQL that calculates ‘Recency’ and ‘Frequency’ using SQL window functions, and then call this stored procedure from your Snowpark Python code.

Write custom Python code in a Snowpark UDF to retrieve each transaction for a customer and calculate recency and frequency directly in Python without pandas.

NO.110 You are using a Snowflake Notebook to analyze customer churn for a telecommunications company. You have a dataset with millions of rows and want to perform feature engineering using a combination of SQL transformations and Python code. Your goal is to create a new feature called ‘average_monthly call_duration’ which calculates the average call duration for each customer over the last 3 months. You are using the Snowpark DataFrame API within your notebook. Given the following code snippet to start with:

Option A

Option B

Option C

Option D

Option E

NO.111 You are tasked with performing data profiling on a large customer dataset in Snowflake to identify potential issues with data quality and discover initial patterns. The dataset contains personally identifiable information (PII). Which of the following Snowpark and SQL techniques would be most appropriate to perform this task while minimizing the risk of exposing sensitive data during the exploratory data analysis phase?

Directly query the raw customer data using SQL and Snowpark, computing descriptive statistics like mean, median, and standard deviation for all numeric columns and frequency counts for categorical columns. Store the results in a temporary table for further analysis.

Utilize Snowpark to create a sampled dataset (e.g., 1% of the original data) and perform all exploratory data analysis on the sample to reduce the data volume and potential exposure of PII.

Apply differential privacy techniques using Snowpark to add noise to the summary statistics generated from the customer data, masking the individual contributions of each customer while revealing overall trends.

Create a masked view of the customer data using Snowflake’s dynamic data masking features. This view masks sensitive PII columns while allowing you to compute aggregate statistics and identify patterns using SQL and Snowpark functions. Columns like ’email’ are masked using and columns like are masked using .

Export the entire customer dataset to an external data lake for exploratory analysis using Spark and Python. Apply data masking in Spark before analysis.

NO.112 You are designing a feature engineering pipeline using Snowpark Feature Store for a fraud detection model. You have a transaction table in Snowflake. One crucial feature is the ‘average_transaction_amount_last_7_days’ for each customer. You want to implement this feature using Snowpark Python and materialize it in the Feature Store. You have the following Snowpark DataFrame ‘transactions_df containing ‘customer_id’ and ‘transaction_amount’. Which of the following code snippets correctly defines and registers this feature in the Snowpark Feature Store, ensuring efficient computation and storage?

NO.113 You are validating a time series forecasting model for daily sales using Snowflake and Snowpark. The residuals plot shows a clear sinusoidal pattern. Which of the following actions should you consider to improve your model? (Select all that apply)

Increase the regularization strength in your model.

Incorporate lagged features representing previous sales values (e.g., sales from the previous day, week, or month).

Apply a Box-Cox transformation to the target variable (sales) to stabilize the variance.

Remove outlier data points to improve overall model performance.

Change the algorithm to a linear regression model, since it is more likely to capture sinusoidal patterns

NO.114 A retail company is using Snowflake to store sales data’. They have a table called ‘SALES DATA’ with columns: ‘SALE ID’, ‘PRODUCT D’, ‘SALE DATE’, ‘QUANTITY’ , and ‘PRICE’. The data scientist wants to analyze the trend of daily sales over the last year and visualize this trend in Snowsight to present to the business team. Which of the following approaches, using Snowsight and SQL, would be the most efficient and appropriate for visualizing the daily sales trend?

Use the Snowsight web UI to manually filter the ‘SALES_DATX table by ‘SALE_DATE for the last year and create a bar chart showing ‘SALE_ID count per day.

Write a SQL query that calculates the daily total sales amount CSUM(QUANTITY PRICEY) for the last year and use Snowsight’s charting options to generate a line chart with ‘SALE DATE on the x-axis and daily sales amount on the y-axis.

Export all the data from the ‘SALES DATA’ table to a CSV file and use an external tool like Python’s Matplotlib or Tableau to create the visualization.

Create a Snowflake view that aggregates the daily sales data, then use Snowsight to visualize the view data as a table without any chart.

Write a SQL query that uses ‘DATE TRUNC(‘day’, SALE DATE)’ to group sales by day and calculate the total sales (SUM(QUANTITY PRICE)). Use Snowsight’s line chart option with the truncated date on the x-axis and total sales on the y-axis, filtering by ‘SALE_DATE’ within the last year. Furthermore, use moving average with window function to smooth the data.

NO.115 You have trained a classification model in Snowflake using Snowpark ML to predict customer churn. After deploying the model, you observe that the model performs well on the training data but poorly on new, unseen data’. You suspect overfitting. Which of the following strategies can be applied within Snowflake to detect and mitigate overfitting during model validation , considering the model is already deployed and receiving inference requests through a Snowflake UDF?

Calculate the Area Under the Precision-Recall Curve (AUPRC) using Snowflake SQL on both the training and validation datasets. A significant difference indicates overfitting. Then, retrain the model in Snowpark ML with added L1 or L2 regularization, adjusting the regularization strength based on validation set performance, and redeploy the UDF.

Monitor the UDF execution time in Snowflake. A sudden increase in execution time indicates overfitting. Use the ‘EXPLAIN’ command on the UDF’s underlying SQL query to identify performance bottlenecks and rewrite the query for optimization.

Implement k-fold cross-validation within the Snowpark ML training pipeline using Snowflake’s distributed compute. Track the mean and standard deviation of the performance metrics (e.g., accuracy, Fl-score) across folds. A high variance suggests overfitting. Use this information to tune hyperparameters or select a simpler model architecture before deployment.

Create shadow UDFs that score data using alternative models. Compare the performance metrics (such as accuracy, precision, recall) between the production UDF and shadow UDFs using Snowflake’s query capabilities. If shadow models consistently outperform the production model on certain data segments, retrain the production model incorporating those data segments with higher weights.

Since the model is already deployed, the only option is to collect inference requests and compare the distributions of predicted values in each batch with the predicted values on the training set. A large difference indicates overfitting; model must be retrained outside of the validation process.

NO.116 You are deploying a time series forecasting model in Snowflake. You need to log the performance metrics (e.g., MAE, RMSE) of the model after each prediction run to the Snowflake Model Registry. Which of the following steps are necessary to achieve this?

Use the method with the ‘metrics’ parameter to log the metrics directly during model registration.

Create a separate table in Snowflake to store the performance metrics and use SQL “INSERT statements to log the metrics after each prediction run.

Use the method to log individual metrics to the Model Registry associated with a specific model version after the prediction run.

Leverage Snowflake’s Event Tables to capture and store metrics data generated during model evaluation and prediction workflows and then access via stored procedures that log to the Model Registry.

You must create a custom logging solution outside of Snowflake using external services and then integrate those logs back into Snowflake via external functions and Model Registry APIs

NO.117 You are tasked with identifying Personally Identifiable Information (PII) within a Snowflake table named ‘customer data’. This table contains various columns, some of which may contain sensitive information like email addresses and phone numbers. You want to use Snowflake’s data governance features to tag these columns appropriately. Which of the following approaches is the MOST effective and secure way to automatically identify and tag potential PII columns with the ‘PII CLASSIFIED tag in your Snowflake environment, ensuring minimal manual intervention and optimal accuracy?

Create a custom Snowpark for Python UDF that uses regular expressions to analyze the data in each column and apply the ‘PII_CLASSIFIED tag if a match is found. Schedule this UDF to run periodically using Snowflake Tasks.

Use Snowflake’s built-in classification feature with a pre-defined sensitivity category to identify potential PII columns. Associate a masking policy that redacts the data, and apply a tag ‘PII_CLASSIFIED’ via automated tagging to the columns identified as containing PII.

Manually inspect each column in the ‘customer_data’ table and apply the ‘PII_CLASSIFIED’ tag to columns that appear to contain PII based on their names and a small sample of data.

Write a SQL script to query the ‘INFORMATION SCHEMA.COLUMNS’ view, identify columns with names containing keywords like ’email’ or ‘phone’, and then apply the ‘PII_CLASSIFIED tag to those columns.

Export the ‘customer_data’ to a staging area in cloud storage, use a third-party data discovery tool to scan for PII, and then manually apply the “PII_CLASSIFIED’ tag to the corresponding columns in Snowflake based on the tool’s findings.

NO.118 A data scientist is tasked with identifying customer segments for a new marketing campaign using transaction data stored in Snowflake. The transaction data includes features like transaction amount, frequency, recency, and product category. Which unsupervised learning algorithm would be MOST appropriate for this task, considering scalability and Snowflake’s data processing capabilities, and what preprocessing steps are crucial before applying the algorithm?

K-Means clustering, after standardizing numerical features (transaction amount, frequency, recency) and using one-hot encoding for product category. This is highly scalable within Snowflake using UDFs and SQL.

Hierarchical clustering, using the complete linkage method and Euclidean distance. No preprocessing is necessary, as hierarchical clustering can handle raw data.

DBSCAN, using raw data without any scaling or encoding. The algorithm’s density-based nature will automatically handle the varying scales of the features.

Principal Component Analysis (PCA) followed by K-Means. This reduces dimensionality and then clusters, improving the visualization of the cluster.

K-Means clustering, after applying min-max scaling to numerical features and converting categorical features to numerical representation. The optimal ‘k’ (number of clusters) should be determined using the elbow method or silhouette analysis.

NO.119 Consider the following Snowflake SQL query used to calculate the RMSE for a regression model’s predictions, where ‘actual_value’ is the actual value and ‘predicted value’ is the model’s prediction. However, you notice that the RMSE calculation is incorrect due to an error in the query. Identify the error in the query and provide the corrected query. The table name is ‘sales_predictions’.

Which of the following options represents the corrected query that accurately calculates the RMSE?

NO.120 You are tasked with analyzing the ‘transaction amounts’ column in the ‘sales data’ table to understand its variability across different geographical regions. You need to calculate the variance of transaction amounts for each region. However, some regions have very few transactions, which can skew the variance calculation. Which of the following SQL statements correctly calculates the variance for each region, excluding regions with fewer than 10 transactions, using Snowflake’s native statistical functions?

Option A

Option B

Option C

Option D

Option E

NO.121 A data scientist is using Snowflake to perform anomaly detection on sensor data from industrial equipment. The data includes timestamp, sensor ID, and sensor readings. Which of the following approaches, leveraging unsupervised learning and Snowflake features, would be the MOST efficient and scalable for detecting anomalies, assuming anomalies are rare events?

Use a Support Vector Machine (SVM) with a radial basis function (RBF) kernel trained on the entire dataset to classify data points as normal or anomalous. Implement the SVM model as a Snowflake UDF.

Implement an Isolation Forest model. Train the Isolation Forest model on a representative sample of the sensor data and create UDF to score each row in snowflake.

Use K-Means clustering to group sensor readings into clusters and identify data points that are far from the cluster centroids as anomalies. No model training necessary.

Calculate the moving average of sensor readings over a fixed time window using Snowflake SQL and flag data points that deviate significantly from the moving average as anomalies. No ML model needed.

Apply Autoencoders to the sensor data using a Snowflake external function. Data points are considered anomalous if the reconstruction error from the autoencoder exceeds a certain threshold.

NO.122 You are building a machine learning model using Snowflake data to predict customer churn. Your dataset includes a ‘CUSTOMER TYPE column with the following possible values: ‘New’, ‘Returning’, and ‘VIP’. You need to perform one-hot encoding on this column. Which of the following Snowflake SQL queries correctly implements one-hot encoding for the ‘CUSTOMER TYPE column, creating separate binary columns for each customer type (‘IS NEW’, ‘IS RETURNING’, ‘IS VIP’)?

Option A

Option B

Option C

Option D

Option E

NO.123 You are building a customer churn prediction model for a telecommunications company. You have a ‘CUSTOMER DATA’ table with a ‘MONTHLY SPENDING’ column that represents the customer’s monthly bill amount. You want to binarize this column to create a feature indicating whether a customer is a ‘High Spender’ or ‘Low Spender’. You decide that customers spending more than $75 are ‘High Spenders’. Which of the following Snowflake SQL statements is the most efficient and correct way to achieve this, considering performance and readability, while avoiding potential NULL values in the resulting binarized column?

Option A

Option B

Option C

Option D

Option E

NO.124 You are developing a regression model in Snowflake to predict housing prices. You’ve trained a model using Snowflake ML functions and now need to rigorously validate its performance. You have a separate validation dataset stored in a table named ‘HOUSING VALIDATION’. Which of the following SQL statements, when executed in Snowflake, would accurately calculate the Root Mean Squared Error (RMSE) of your model’s predictions against the actual prices in the validation dataset, assuming your model is named ‘HOUSING PRICE MODEL’ and the prediction function generated by CREATE SNOWFLAKE.ML.FORECAST is called PREDICT?

Option A

Option B

Option C

Option D

Option E

NO.125 You are building a machine learning model to predict loan defaults. You have a dataset in Snowflake with the following features: ‘income’ (annual income in USD), ‘loan_amount’ (loan amount in USD), and ‘credit_score’ (FICO score). You need to normalize these features before training your model. The data has outliers in both ‘income’ and ‘loan_amount’, and ‘credit_score’ has a roughly normal distribution but you still want to standardize it to have a mean of 0 and standard deviation of 1. You want to perform these normalizations using only SQL in Snowflake (no UDFs). Which of the following SQL transformations are most suitable?

Option A

Option B

Option C

Option D

Option E

NO.126 You’ve built a model in Snowflake to predict house prices based on features like location, square footage, and number of bedrooms. After deploying the model, you want to ensure that the incoming data used for prediction is similar to the data the model was trained on. You decide to implement a data distribution comparison strategy. Consider these options and select all that apply:

Calculate the mean and standard deviation for each numerical feature in both the training and incoming datasets using Snowflake SQL. Create a Snowflake Alert that triggers if the difference in means or standard deviations exceeds a predefined threshold for any feature.

Generate histograms for each numerical feature in both the training and incoming datasets using a Python UDF that leverages libraries like Pandas and Matplotlib. Visually compare the histograms to identify potential distribution shifts.

Use Snowflake’s built-in statistics functions to compute quantiles (e.g., 25th, 50th, 75th percentiles) for each numerical feature. Compare these quantiles between the training and incoming datasets and set up alerts for significant deviations.

Only focus on monitoring the target variable (house price) and assume that if the distribution of house prices remains stable, the input data distribution is also stable.

Create a binary classification model in Snowflake that attempts to predict whether a given row of data comes from the training dataset or the incoming dataset. If the model achieves high accuracy, it indicates a significant difference in data distributions.

[Mar-2026] DSA-C03 Dumps PDF – DSA-C03 Real Exam Questions Answers [Q102-Q126]

admin

Leave a Reply Cancel reply

Related posts:

admin

You might also like

Leave a Reply Cancel reply