Snowflake DSA-C03 - SnowPro Advanced: Data Scientist Certification Exam

A data scientist is building a linear regression model in Snowflake to predict customer churn based on structured data stored in a table named 'CUSTOMER DATA'. The table includes features like 'CUSTOMER D', 'AGE, 'TENURE MONTHS', 'NUM PRODUCTS', and 'AVG MONTHLY SPEND'. The target variable is 'CHURNED' (1 for churned, 0 for active). After building the model, the data scientist wants to evaluate its performance using Mean Squared Error (MSE) on a held-out test set. Which of the following SQL queries, executed within Snowflake's stored procedure framework, is the MOST efficient and accurate way to calculate the MSE for the linear regression model predictions against the actual 'CHURNED values in the 'CUSTOMER DATA TEST table, assuming the linear regression model is named 'churn _ model' and the predicted values are generated by the MODEL APPLY() function?

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

You have trained a fraud detection model using scikit-learn and want to deploy it in Snowflake using the Snowflake Model Registry. You've registered the model as 'fraud _ model' in the registry. You need to create a Snowflake user-defined function (UDF) that loads and executes the model. Which of the following code snippets correctly creates the UDF, assuming the model is a serialized pickle file stored in a stage named 'model_stage'?

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

You've deployed a fraud detection model in Snowflake. The model is implemented as a Python UDF that uses a pre-trained scikit-learn model stored as a stage file. Your goal is to enable near real-time fraud detection on incoming transactions. Due to regulatory requirements, you need to maintain a detailed audit trail of all predictions, including the input features, model version, prediction scores, and any errors encountered during the prediction process. Which of the following approaches are valid and efficient for storing these audit logs and predictions in Snowflake?

• A. Utilize Snowflake's Streams and Tasks to automatically capture changes to the transaction table and trigger the prediction UDF, storing the audit logs in a separate table with similar structure as described in option A.
• B. Create a dedicated table with columns for transaction ID, input features (as a JSON VARIANT), model version, prediction score, error message (if any), and prediction timestamp. Use a Snowflake Sequence to generate unique log IDs.
• C. Use Snowflake's 'SYSTEM$QUERY LOG' table to extract information about the UDF execution and join it with the transaction data to reconstruct the audit trail.
• D. Store the audit logs as unstructured text files in an external stage (e.g., AWS S3) and periodically load them into a Snowflake table using COPY INTO command.
• E. Log the audit information to an external logging service (e.g., Splunk) using an external function called from within the UDF.

You've deployed a fraud detection model in Snowflake using Snowpark. You are monitoring its performance and notice a significant decrease in recall, while precision remains high. This means the model is missing many fraudulent transactions. The training data was initially balanced, but you suspect that recent changes in user behavior have skewed the distribution of fraudulent vs. non-fraudulent transactions in production. Which of the following actions are MOST appropriate to address this issue and improve the model's performance, considering best practices for model retraining within the Snowflake ecosystem?

• A. Adjust the model's classification threshold to be more sensitive, even if it means accepting a slightly lower precision. This can be done directly within Snowflake using a SQL UDF that transforms the model's output probabilities.
• B. Retrain the model using the original training data. Since the precision is high, the model's fundamental logic is still sound. A larger training dataset isn't necessary.
• C. Retrain the model using a dataset that includes recent production data, being sure to re-balance the dataset to maintain a roughly equal number of fraudulent and non-fraudulent transactions. Prioritize transactions from the last month.
• D. Implement a data drift monitoring system in Snowflake to automatically detect changes in the input features of the model. Trigger an automated retraining pipeline when significant drift is detected. This retraining should include recent production data with updated labels, but only if label data collection can be automated.
• E. Immediately shut down the model to prevent further inaccurate classifications. Investigate why the recall is low before any retraining is performed.

A retail company, 'GlobalMart,' wants to optimize its product placement strategy in its physical stores. They have transactional data stored in Snowflake, capturing which items are purchased together in the same transaction. They aim to use association rule mining to identify frequently co-occurring items. Given the following simplified transactional data in a Snowflake table named 'SALES TRANSACTIONS:

Which of the following SQL-based approaches, combined with Snowpark Python for association rule generation (using a library like 'mlxtend'), would be the MOST efficient and scalable way to prepare this data for association rule mining, specifically focusing on converting it into a transaction-item matrix suitable for algorithms like Apriori? Assume 'spark' is a 'snowpark.Session' object connected to your Snowflake environment.

• A. Employing a custom UDF (User-Defined Function) written in Java or Scala that directly processes the transactional data within Snowflake and outputs the transaction-item matrix in a format suitable for Snowpark. This offloads processing to compiled code within Snowflake, maximizing performance.
• B. Creating a temporary table in Snowflake using a SQL query that aggregates items by transaction and represents them in a format suitable for Snowpark's 'mlxtend' library. Then load this temporary table into a Snowpark DataFrame and use it as input to the Apriori algorithm.
• C. Using Snowpark's 'DataFrame.groupBy(V and functions to aggregate items by transaction ID, then pivoting the data using to create the transaction-item matrix. This approach requires loading all data into the Snowpark DataFrame before pivoting.
• D. First extracting all the data from snowflake into pandas dataframe and then use pivoting and other pandas operations to convert to the needed format.
• E. Utilizing Snowflake's SQL function within a stored procedure to concatenate items purchased in each transaction into a string, then processing the string using Python in Snowpark to create the transaction-item matrix. This approach minimizes data transfer but introduces string parsing overhead in Python.