You have deployed a fraud detection model in Snowflake and are monitoring its performance. The initial AUC was 0.92. After a month, you observe the AUC has dropped to 0.78. You suspect data drift. Which of the following steps should you take FIRST to investigate and address this performance degradation, focusing on efficient resource utilization within Snowflake?

• A. Immediately retrain the model using the entire dataset available, scheduling a Snowpark Python UDF to perform the training.
• B. Analyze the distributions of key features in the current production data compared to the training data using Snowflake SQL queries and visualization tools. Specifically compare the distributions of features such as transaction amount and time of day. Then, if drift is confirmed, retrain using updated data.
• C. Increase the complexity of the existing model architecture by adding more layers to the neural network to improve its adaptability.
• D. Delete the existing model and deploy a pre-trained, generic fraud detection model obtained from a public repository.
• E. Deploy a new model version with a higher classification threshold to compensate for the increased false positives.

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. Increase the value of 'MAX BATCH_ROWS' for the UDF to process larger batches of data at once.
• C. Partition the input data into smaller chunks using SQL queries and call the UDF on each partition separately.
• D. 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.
• E. Reduce the value of 'MAX for the UDF to process smaller batches of data.

Consider you are working on a credit risk scoring model using Snowflake. You have a table 'credit data' with the following schema: 'customer id', 'age', 'income', 'credit_score', 'loan_amount', 'loan_duration', 'defaulted'. You want to create several new features using Snowflake SQL to improve your model. Which combination of the following SQL statements will successfully create features for age groups, income-to-loan ratio, and interaction between credit score and loan amount using SQL in Snowflake? Choose all that apply.

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

You are tasked with identifying fraudulent transactions from unstructured log data stored in Snowflake. The logs contain various fields, including timestamps, user IDs, and transaction details embedded within free-text descriptions. You plan to use a supervised learning approach, having labeled a subset of transactions as 'fraudulent' or 'not fraudulent.' Which of the following methods best describes the extraction and processing of this data for training a machine learning model within Snowflake?

• A. Use a combination of regular expressions and natural language processing (NLP) techniques within Snowflake UDFs to extract key features such as transaction amounts, product categories, and sentiment scores from the log descriptions. Then, combine these extracted features with other structured data (e.g., user demographics) and train a classification model using these features. The NLP steps include tokenization, stop word removal, and TF-IDF vectorization.
• B. Export the entire log data to an external machine learning platform (e.g., AWS SageMaker) and perform feature extraction, NLP processing, and model training there. Import the trained model back into Snowflake as a UDF for prediction.
• C. Use regular expressions within a Snowflake UDF to extract relevant information (e.g., amount, item description) from the log descriptions. Convert extracted data into numerical features using one-hot encoding within the UDF. Then, train a model using the extracted numerical features directly within Snowflake using SQL extensions for machine learning.
• D. Extract the entire log description field and train a word embedding model (e.g., Word2Vec) on the entire dataset. Average the word vectors for each transaction's log description to create a document vector. Train a classification model (e.g., Random Forest) on these document vectors within Snowflake.
• E. Treat the unstructured log description as a categorical feature and directly apply one-hot encoding within Snowflake, then train a classification model. Due to high dimensionality perform PCA for dimensionality reduction before training.

You are using Snowflake ML to train a binary classification model. After training, you need to evaluate the model's performance. Which of the following metrics are most appropriate to evaluate your trained model, and how do they differ in their interpretation, especially when dealing with imbalanced datasets?

• A. Accuracy: It measures the overall correctness of the model. Precision: It measures the proportion of positive identifications that were actually correct. Recall: It measures the proportion of actual positives that were identified correctly. Fl-score: It is the harmonic mean of precision and recall.
• B. Confusion Matrix: A table that describes the performance of a classification model by showing the counts of true positive, true negative, false positive, and false negative predictions. This isnt a metric but representation of the metrics.
• C. AUC-ROC: Measures the ability of the model to distinguish between classes. It is less sensitive to class imbalance than accuracy. Log Loss: Measures the performance of a classification model where the prediction input is a probability value between 0 and 1.
• D. Mean Squared Error (MSE): The average squared difference between the predicted and actual values. R-squared: Represents the proportion of variance in the dependent variable that is predictable from the independent variables. These are great for regression tasks.
• E. Precision, Recall, F I-score, AUC-ROC, and Log Loss: Precision focuses on the accuracy of positive predictions; Recall focuses on the completeness of positive predictions; Fl-score balances Precision and Recall; AUC-ROC evaluates the separability of classes and Log Loss quantifies the accuracy of probabilities, especially valuable for imbalanced datasets because they provide a more nuanced view of performance than accuracy alone.