Snowflake DSA-C03 real exam prep : SnowPro Advanced: Data Scientist Certification Exam

You are building a fraud detection model using Snowflake data'. The dataset 'TRANSACTIONS' contains billions of records and is partitioned by 'TRANSACTION DATE'. You want to use cross-validation to evaluate your model's performance on different subsets of the data and ensure temporal separation of training and validation sets. Given the following Snowflake table structure:

Which approach would be MOST appropriate for implementing time-based cross-validation within Snowflake to avoid data leakage and ensure robust model evaluation? (Assume using Snowpark Python to develop)

• A. Explicitly define training and validation sets based on date ranges within the Snowpark Python environment, performing iterative training and evaluation within the client environment before deploying a model to Snowflake. No built-in cross-validation used
• B. Create a UDF that assigns each row to a fold based on the 'TRANSACTION DATE column using a modulo operation. This is then passed to the 'cross_validation' function in Snowpark ML.
• C. Implement a custom splitting function within Snowpark, creating sequential folds based on the 'TRANSACTION DATE column and use that with Snowpark ML's cross_validation. Ensure each fold represents a distinct time window without overlap.
• D. Use 'SNOWFLAKE.ML.MODEL REGISTRY.CREATE MODEL' with default settings, which automatically handles temporal partitioning based on the insertion timestamp of the data.
• E. Utilize the 'SNOWFLAKE.ML.MODEL REGISTRY.CREATE MODEL' with the 'input_colS argument containing 'TRANSACTION DATE'. Snowflake will automatically infer the temporal nature of the data and perform time-based cross-validation.

You are building a multi-class classification model in Snowflake to predict the category of customer support tickets (e.g., 'Billing', 'Technical Support', 'Sales Inquiry', 'Account Management', 'Feature Request') based on the ticket's text content. The initial model evaluation shows an overall accuracy of 75%, but the 'Feature Request' category has a significantly lower precision and recall compared to other categories. Which of the following strategies would be MOST effective in addressing this issue, considering the limitations and advantages of Snowflake's data processing capabilities and typical machine learning practices?

• A. Increase the threshold for classifying a ticket as 'Feature Request' to improve precision, even if it further reduces recall. This prioritizes accurate identification of feature requests over capturing all of them.
• B. Apply a cost-sensitive learning approach during model training, assigning a higher misclassification cost to errors involving the 'Feature Request' category. This encourages the model to prioritize correctly classifying feature requests.
• C. Oversample the 'Feature Request' category in the training dataset before training the model. This involves creating synthetic data points or duplicating existing data to balance the class distribution. This can be done using SQL and Snowflake's internal stage for storing temporary data before training.
• D. All of the above.
• E. Engineer new features specifically designed to improve the model's ability to distinguish 'Feature Request' tickets from other categories. This could involve creating sentiment scores for 'innovation' or using topic modeling to identify key themes related to feature requests.

You're building a model to predict whether a user will click on an ad (binary classification: click or no-click) using Snowflake. The data is structured and includes features like user demographics, ad characteristics, and past user interactions. You've trained a logistic regression model using SNOWFLAKE.ML and are now evaluating its performance. You notice that while the overall accuracy is high (around 95%), the model performs poorly at predicting clicks (low recall for the 'click' class). Which of the following steps could you take to diagnose the issue and improve the model's ability to predict clicks, and how would you implement them using Snowflake SQL? SELECT ALL THAT APPLY.

• A. Implement feature engineering by creating interaction terms or polynomial features from existing features using SQL, to capture potentially non-linear relationships between features and the target variable. Example:
  
• B. Generate a confusion matrix using SQL to visualize the model's performance across both classes. Example SQL:
  
• C. Increase the complexity of the model by switching to a non-linear algorithm like Random Forest or Gradient Boosting without performing hyperparameter tuning, as more complex models always perform better.
• D. Calculate precision, recall, F I-score, and AUC for the 'click' class using SQL queries to get a more detailed understanding of the model's performance on the minority class. Example:
  
• E. Reduce the amount of training data to avoid overfitting. Overfitting is known to produce low recall for the 'click' class.

You have deployed a vectorized Python UDF in Snowflake to perform sentiment analysis on customer reviews. The UDF uses a pre-trained transformer model loaded from a Stage. The model consumes a significant amount of memory (e.g., 5GB). Users are reporting intermittent 'Out of Memory' errors when calling the UDF, especially during peak usage. Which of the following strategies, used IN COMBINATION, would MOST effectively mitigate these errors and optimize resource utilization?

• A. Increase the warehouse size to provide more memory per node.
• B. Implement lazy loading of the model within the UDF, ensuring it's only loaded once per warehouse node and reused across multiple invocations within that node.
• C. Increase the value of 'MAX BATCH_ROWS' for the UDF to process larger batches of data at once.
• D. Partition the input data into smaller chunks using SQL queries and call the UDF on each partition separately.
• E. Reduce the value of 'MAX for the UDF to process smaller batches of data.

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:

• A. Option A
• B. Option C
• C. Option D
• D. Option E
• E. Option B