Anomaly Detection with Snowflake ML Functions

Snowflake 2024    |    Expert
  • 12 videos | 1h 36m 13s
  • Includes Assessment
  • Earns a Badge
Rating 5.0 of 1 users Rating 5.0 of 1 users (1)
Snowflake ML functions offer powerful SQL functionality for several common use cases, including anomaly detection, time series forecasting, and classification. In this course, learn about the types of models available in Snowflake ML functions, when to use functions for different machine learning Snowflake tasks, and the required data formats for input into anomaly detection and forecasting models. Next, examine how to use Snowflake ML functions to implement anomaly detection, interpret the output of the anomaly detection model, and tune model sensitivity and save model results. Finally, discover how to add exogenous variables for anomaly detection model enhancement and extend a model to work with multi-series data. After completing this course, you will be able to implement anomaly detection with Snowflake ML functions.

WHAT YOU WILL LEARN

  • Discover the key concepts covered in this course
    List the types of models available in snowflake ml functions such as anomaly detection, forecasting, and contribution explorer
    Identify the form of data required for input to anomaly detection and forecasting models and differentiate single and multi time series data
    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
    Use snowflake ml functions to train a single-series unsupervised anomaly detection model
  • Invoke the anomaly detection function, interpret the results, and save them to a table
    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
    Save model results to a table using sqlid and the result_scan function, then calibrate model sensitivity using prediction_interval
    Extend the single-series anomaly detection model by adding exogenous variables and observe changes in model sensitivity and feature importance scores
    Extend the anomaly detection model to work with multi-series data and verify that model feature scores are now reported for each series
    Summarize the key concepts covered in this course

IN THIS COURSE

  • 1m 57s
    In this video, we will discover the key concepts covered in this course. FREE ACCESS
  • 9m 49s
    After completing this video, you will be able to list the types of models available in Snowflake ML functions such as anomaly detection, forecasting, and Contribution Explorer. FREE ACCESS
  • Locked
    3.  Single and Multi Time Series Data
    7m 24s
    Upon completion of this video, you will be able to identify the form of data required for input to anomaly detection and forecasting models and differentiate single and multi time series data. FREE ACCESS
  • Locked
    4.  Implement Anomaly Detection and Forecasting with ML Functions
    7m 38s
    In this video, we will outline the steps for training an anomaly detection model and how to use it for prediction. FREE ACCESS
  • Locked
    5.  Analysis of Anomaly Detection Output
    10m 9s
    Through this video, you will be able to recognize how to analyze each column in the output of the anomaly detection model. FREE ACCESS
  • Locked
    6.  Creating a Single-series Unsupervised Anomaly Detection ML Function
    8m 54s
    Learn how to use Snowflake ML functions to train a single-series unsupervised anomaly detection model. FREE ACCESS
  • Locked
    7.  Invoking an Anomaly Detection Function
    12m 44s
    In this video, find out how to invoke the anomaly detection function, interpret the results, and save them to a table. FREE ACCESS
  • Locked
    8.  Creating an Anomaly Detection Model Using Snowflake ML Functions
    9m 22s
    Discover how to 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. FREE ACCESS
  • Locked
    9.  Tuning Model Sensitivity with the Prediction Interval
    11m 22s
    In this video, you will learn how to save model results to a table using SQLID and the RESULT_SCAN function, then calibrate model sensitivity using prediction_interval. FREE ACCESS
  • Locked
    10.  Adding Exogenous Variables to an Anomaly Detection Model
    9m 12s
    During this video, discover how to extend the single-series anomaly detection model by adding exogenous variables and observe changes in model sensitivity and feature importance scores. FREE ACCESS
  • Locked
    11.  Using Anomaly Detection with Multi-series Data
    5m 36s
    Find out how to extend the anomaly detection model to work with multi-series data and verify that model feature scores are now reported for each series. FREE ACCESS
  • Locked
    12.  Course Summary
    2m 6s
    In this video, we will summarize the key concepts covered in this course. FREE ACCESS

EARN A DIGITAL BADGE WHEN YOU COMPLETE THIS COURSE

Skillsoft is providing you the opportunity to earn a digital badge upon successful completion on some of our courses, which can be shared on any social network or business platform.

Digital badges are yours to keep, forever.

YOU MIGHT ALSO LIKE

Course Machine Learning with BigQuery ML: Building Unsupervised Models
Rating 4.3 of 3 users Rating 4.3 of 3 users (3)
Course Snowflake Cortex for LLMs, RAG, and Search
Rating 5.0 of 2 users Rating 5.0 of 2 users (2)
Course Machine Learning with BigQuery ML: Training Time Series Forecasting Models
Rating 2.5 of 2 users Rating 2.5 of 2 users (2)