You have successfully trained a binary classification model using Snowpark ML and deployed it as a UDF in Snowflake. The UDF takes several input features and returns the predicted probability of the positive class. You need to continuously monitor the model's performance in production to detect potential data drift or concept drift. Which of the following methods and metrics, when used together, would provide the MOST comprehensive and reliable assessment of model performance and drift in a production environment? (Select TWO)

• A. Check for null values in the input features passed to the UDF. A sudden increase in null values indicates a problem with data quality.
• B. Monitor the volume of data processed by the UDF per day. A sudden drop in volume indicates a problem with the data pipeline.
• C. Continuously calculate and track performance metrics like AUC, precision, recall, and Fl-score on a representative sample of labeled production data over regular intervals. Compare these metrics to the model's performance on the holdout set during training.
• D. Calculate the Kolmogorov-Smirnov (KS) statistic between the distribution of predicted probabilities in the training data and the production data over regular intervals. Track any substantial changes in the KS statistic.
• E. Monitor the average predicted probability score over time. A significant shift in the average score indicates data drift.

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?

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

You are building a data science pipeline in Snowflake to predict customer churn. The pipeline includes a Python UDF that uses a pre- trained scikit-learn model stored as a binary file in a Snowflake stage. The UDF needs to load this model for prediction. You've encountered an issue where the UDF intermittently fails, seemingly related to resource limits when multiple concurrent queries invoke the UDF. Which of the following strategies would best optimize the UDF for concurrency and resource efficiency, minimizing the risk of failure?

• A. Load the scikit-learn model inside the UDF function on every invocation to ensure the latest version is used.
• B. Load the scikit-learn model outside the UDF function in the global scope of the module so that all invocations share the same loaded model instance. Use the 'context.getExecutionContext(Y to track execution, making sure it is thread safe.
• C. Utilize Snowflake's session-level caching by storing the loaded model in 'session.get('model')' to be reused across multiple UDF calls within the same session. Reload the model if 'session.get('model')' is None.
• D. Increase the memory allocated to the Snowflake warehouse to accommodate multiple UDF invocations.
• E. Implement a global, lazy-loaded cache for the scikit-learn model within the UDF's module. The model is loaded only once during the first invocation and shared across subsequent calls. Protect the loading process with a lock to prevent race conditions in concurrent environments.

A marketing analyst is building a propensity model to predict customer response to a new product launch. The dataset contains a 'City' column with a large number of unique city names. Applying one-hot encoding to this feature would result in a very high-dimensional dataset, potentially leading to the curse of dimensionality. To mitigate this, the analyst decides to combine Label Encoding followed by binarization techniques. Which of the following statements are TRUE regarding the benefits and challenges of this combined approach in Snowflake compared to simply label encoding?

• A. Label encoding introduces an arbitrary ordinal relationship between the cities, which may not be appropriate. Binarization alone cannot remove this artifact.
• B. While label encoding itself adds an ordinal relationship, applying binarization techniques like binary encoding (converting the label to binary representation and splitting into multiple columns) after label encoding will remove the arbitrary ordinal relationship.
• C. Binarizing a label encoded column using a simple threshold (e.g., creating a 'high_city_id' flag) addresses the curse of dimensionality by reducing the number of features to one, but it loses significant information about the individual cities.
• D. Label encoding followed by binarization will reduce the memory required to store the 'City' feature compared to one-hot encoding, and Snowflake's columnar storage optimizes storage for integer data types used in label encoding.
• E. Binarization following label encoding may enhance model performance if a specific split based on a defined threshold is meaningful for the target variable (e.g., distinguishing between cities above/below a certain average income level related to marketing success).

You are analyzing website clickstream data stored in Snowflake to identify user behavior patterns. The data includes user ID, timestamp, URL visited, and session ID. Which of the following unsupervised learning techniques, combined with appropriate data transformations in Snowflake SQL, would be most effective in discovering common navigation paths followed by users? (Choose two)

• A. Association rule mining (e.g., Apriori) applied directly to the raw URL data to find frequent itemsets of URLs visited together within the same session. No SQL transformations are required.
• B. DBSCAN clustering on the raw URL data, treating each URL as a separate dimension. This will identify URLs that are frequently visited by many users.
• C. Principal Component Analysis (PCA) to reduce the dimensionality of the URL data, followed by hierarchical clustering. This will group similar URLs together.
• D. Sequence clustering using time-series analysis techniques (e.g., Hidden Markov Models), after transforming the data into a sequence of URLs for each session using Snowflake's LISTAGG function ordered by timestamp.
• E. K-Means clustering on features extracted from the URL data, such as the frequency of visiting specific domains or the number of pages visited per session. This requires feature engineering using SQL.