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. 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.
• B. 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.
• 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. 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.
• E. Immediately shut down the model to prevent further inaccurate classifications. Investigate why the recall is low before any retraining is performed.

You are building a model training pipeline in Snowflake using Snowpark Python. You want to leverage a pre-trained model from Hugging Face Transformers for a text classification task, fine-tuning it with your own labeled data stored in a Snowflake table named 'training_data'. You've chosen the 'transformers' library and plan to use a 'transformers.pipeline' for inference. Which of the following code snippets, when integrated into your Snowpark Python application, will correctly download the pre trained model and tokenizer, prepare the data, perform fine-tuning, and then save the fine-tuned model to a Snowflake stage?

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

You have a binary classification model deployed in Snowflake to predict customer churn. The model outputs a probability score between 0 and 1. You've calculated the following confusion matrix on a holdout set: I I Predicted Positive I Predicted Negative I --1 1 Actual Positive | 80 | 20 | I Actual Negative | 10 | 90 | What are the Precision, Recall, and Accuracy for this model, and what do these metrics tell you about the model's performance? SELECT statement given for true and false condition (True Positive, True Negative, False Positive, False Negative)

• A. Precision = 0.80, Recall = 0.89, Accuracy = 0.85. The model is slightly better at identifying true positives than avoiding false positives.
• B. Precision = 0.90, Recall = 0.80, Accuracy = 0.80. The model has good overall performance but needs to be adjusted to improve the false negative rate.
• C. Precision = 0.89, Recall = 0.80, Accuracy = 0.85. The model has good overall performance with balanced precision and recall.
• D. Precision = 0.89, Recall = 0.80, Accuracy = 0.85. The model is slightly better at avoiding false positives than identifying true positives.
  
• E. Precision = 0.80, Recall = 0.90, Accuracy = 0.90. The model is performing poorly, with a high rate of both false positives and false negatives.

You are a data scientist working with a Snowflake table named 'CUSTOMER TRANSACTIONS' that contains sensitive PII data, including customer names and email addresses. You need to create a representative sample of 1% of the data for model development, ensuring that the sample is anonymized and protects customer privacy. The sample must be reproducible for future model iterations.
Which of the following steps are most appropriate using Snowpark for Python and SQL?

• A. Use the 'SAMPLE clause in a SQL query to extract 1% of the rows, then apply SHA256 hashing to the 'customer_name' and 'email_addresS columns within Snowpark using a UDF. Seed the sampling for reproducibility.
• B. Employ stratified sampling based on a customer segment column, then anonymize data. Use the TABLESAMPLE BERNOULLI function in SQL with a 1 percent sample rate. Apply SHA256 hashing to the 'customer_name' and 'email_addresS columns using SQL functions.
• C. Create a new table using 'CREATE TABLE AS SELECT statement combined with 'SAMPLE clause and SHA256 hashing functions in SQL to create the sample and anonymize data. Manually seed the random number generator in Python before executing the SQL statement via Snowpark.
• D. Use Snowpark DataFrame's 'sample' function with a fraction of 0.01 and a fixed random seed. Before sampling, create a view that masks 'customer_name' and 'email_address' columns, and then sample from the view.
• E. Use the 'QUALIFY OVER (ORDER BY RANDOM()) (SELECT COUNT( ) 0.01 FROM CUSTOMER_TRANSACTIONS)' clause with SHA256 on sensitive columns directly within a CREATE TABLE AS statement to generate an anonymized sample. The function should return only 1 percentage of row.