You have a Snowflake Model Registry set up and are managing multiple versions of a machine learning model. You want to programmatically retrieve a specific version of the model and load it for inference within a Snowflake Snowpark Python UDE Assume your registry name is 'my_registry', the model name is 'credit risk_model', and you want to retrieve version 'v2'. How would you achieve this using Snowpark Python?

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

You've trained a model using Snowflake ML and want to deploy it for real-time predictions using a Snowflake UDF. To ensure minimal latency, you need to optimize the UDF's performance. Which of the following strategies and considerations are most important when creating and deploying a UDF for model inference in Snowflake to minimize latency, especially when the model is large (e.g., > 100MB)?
Select all that apply.

• A. Utilize a Snowflake external function instead of a UDF if the model requires access to resources outside of Snowflake's environment.
• B. Store the trained model as a BLOB within the UDF code itself to avoid external dependencies.
• C. Ensure the UDF code is written in Python and utilizes vectorized operations with libraries like NumPy to process data in batches efficiently.
• D. Use a Snowflake Stage to store the model file and load the model within the UDF using 'snowflake.snowpark.files.SnowflakeFile' to minimize memory footprint.
• E. Use smaller warehouse size for UDF evaluation in order to reduce latency and compute costs.

You're developing a model to predict equipment failure using sensor data stored in Snowflake. The dataset is highly imbalanced, with failure events (positive class) being rare compared to normal operation (negative class). To improve model performance, you're considering both up-sampling the minority class and down-sampling the majority class. Which of the following statements regarding the potential benefits and drawbacks of combining up-sampling and down-sampling techniques in this scenario are TRUE? (Select TWO)

• A. The optimal sampling ratio for both up-sampling and down-sampling must always be 1:1, regardless of the initial class distribution.
• B. Over-sampling, combined with downsampling, makes the model more prone to overfitting since this causes the model to train on a large dataset.
• C. Down-sampling, when combined with up-sampling, can exacerbate the risk of losing important information from the majority class, leading to underfitting, especially if the majority class is already relatively small.
• D. Combining up-sampling and down-sampling can lead to a more balanced dataset, potentially improving the model's ability to learn patterns from both classes without introducing excessive bias from solely up-sampling.
• E. Using both up-sampling and down-sampling always guarantees improved model performance compared to using only one of these techniques, regardless of the dataset characteristics.

You are working on a customer churn prediction model and are using Snowpark Feature Store. One of your features, is updated daily. You notice that your model's performance degrades over time, likely due to stale feature values being used during inference. You want to ensure that the model always uses the most up-to-date feature values. Which of the following strategies would be the MOST effective way to address this issue using Snowpark Feature Store and avoid model staleness during online inference?

• A. Configure the Feature Group containing to automatically refresh every hour using a scheduled Snowpark Python function.
• B. Configure with the attribute to manage data staleness and use the during inference, ensuring that the model always uses recent feature values.
• C. Implement a real-time feature retrieval service that directly queries the underlying Snowflake table containing the using Snowpark, bypassing the Feature Store.
• D. Use the method on the Feature Store client during inference, ensuring that you always pass the current timestamp.
• E. Define a custom User-Defined Function (UDF) in Snowflake that retrieves the 'customer_lifetime_value' from the Feature Store on demand whenever the model makes a prediction and set 'feature_retrieval_mode='fresh'S.

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. 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.
• B. 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.
• C. 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.
• D. 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.
• E. 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.