Advanced Analytics and Machine Learning with Snowflake Proficiency (Advanced Level)

Topics covered

• analyze and execute the SQL code generated by the AI & ML Studio from the classification workflow
• analyze and execute the SQL code generated by the AI & ML Studio from the forecasting workflow
• analyze evaluation metrics, global evaluation metrics, and feature importance scores from the output of models created by Snowflake AI & ML Studio
• create an anomaly detection model for single-series data with no exogenous variables using Snowflake ML functions and a filtered query on a multi-series dataset
• extend the anomaly detection model to work with multi-series data and verify that model feature scores are now reported for each series
• extend the single-series anomaly detection model by adding exogenous variables and observe changes in model sensitivity and feature importance scores
• extend time series forecasting models by providing exogenous explanatory variables
• generate SQL code that builds and invokes a time series forecasting model using the AI & ML Studio wizard for forecasting
• generate SQL code that invokes ML classification functions using the AI & ML Studio wizard for classification
• identify how to use the Cortex LLM COMPLETE, EXTRACT_ANSWER, SUMMARIZE, SENTIMENT, and TRANSLATE functions
• identify the form of data required for input to anomaly detection and forecasting models and differentiate single and multi time series data
• identify the uses and steps involved in using Cortex Fine-Tuning with prompt completion pairs in Snowflake
• invoke the anomaly detection function, interpret the results, and save them to a table
• invoke the COMPLETE, EXTRACT_ANSWER, SUMMARIZE, SENTIMENT, and TRANSLATE functions from Python
• invoke the EXPLAIN_FEATURE_IMPORTANCE and SHOW_EVALUATION_METRICS on a time series forecasting model and analyze the results
• invoke the EXTRACT_ANSWER, SUMMARIZE, SENTIMENT, and TRANSLATE functions from SQL
• outline Retrieval Augmented Generation (RAG) and the use of Cortex Search for RAG
• outline the features and functionality of Snowflake Cortex LLMs
• outline the steps for training a forecasting model and using it for prediction
• outline the steps for training an anomaly detection model and how to use it for prediction
• recognize how to analyze each column in the output of the anomaly detection model
• recognize how to use temperature and top_p hyperparameters to determine the predictability of LLM output
• recognize the functionality of Snowflake Copilot, Universal Search, and Document AI
• save model results to a table using SQLID and the RESULT_SCAN function, then calibrate model sensitivity using prediction_interval
• train a model for time series forecasting using ML functions and examine the effects of changing the prediction_interval
• use Snowflake ML functions to train a single-series unsupervised anomaly detection model
• use the COMPLETE Cortex LLM function with different types of roles
• utilize Snowpark ML functions for multi time series forecasting
• utilize the temperature, max_p, and guardrails properties to control the attributes of responses from the COMPLETE Cortex LLM function