Machine Learning Using SAS Viya

This course is part of SAS Machine Learning Engineer Professional Certificate

Instructors: Jeff Thompson

Access provided by RIA PAYMENT INSTITUTION

9,096 already enrolled

9 modules

Gain insight into a topic and learn the fundamentals.

102 reviews

Intermediate level

Some related experience required

Flexible schedule

3 weeks at 10 hours a week

Learn at your own pace

98%

Most learners liked this course

9 modules

Gain insight into a topic and learn the fundamentals.

102 reviews

Intermediate level

Some related experience required

Flexible schedule

3 weeks at 10 hours a week

Learn at your own pace

98%

Most learners liked this course

Skills you'll gain

Tools you'll learn

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

41 assignments

Taught in English

See how employees at top companies are mastering in-demand skills

Learn more about Coursera for Business

logos of Petrobras, TATA, Danone, Capgemini, P&G and L'Oreal

Build your Machine Learning expertise

This course is part of the SAS Machine Learning Engineer Professional Certificate

When you enroll in this course, you'll also be enrolled in this Professional Certificate.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from SAS

There are 9 modules in this course

This course covers the theoretical foundation for different techniques associated with supervised machine learning models. In addition, a business case study is defined to guide participants through all steps of the analytical life cycle, from problem understanding to model deployment, through data preparation, feature selection, model training and validation, and model assessment. A series of demonstrations and exercises is used to reinforce the concepts and the analytical approach to solving business problems.

In this module, you meet the instructor and learn about course logistics, such as how to access the software for this course.

What's included

1 video4 readings1 app item

In this module, you learn how you can meet today's business challenges with machine learning using SAS® Viya®. You start working on the project that runs throughout the course.

What's included

13 videos17 readings6 assignments3 app items

13 videos Total 43 minutes

Introduction 0 minutes
Machine Learning in SAS Viya 2 minutes
Analytics Life Cycle 1 minute
Case Study: Customer Churn 2 minutes
SAS Viya Tools for Machine Learning 2 minutes
Demo: Creating a Project and Loading Data 6 minutes
Predictive Modeling 5 minutes
Data Preparation and Preprocessing 3 minutes
Dividing the Data 4 minutes
Addressing Rare Events Using Event-Based Sampling 3 minutes
Demo: Modifying the Data Partition 6 minutes
Managing Missing Values 3 minutes
Demo: Building a Pipeline from a Basic Template 5 minutes

17 readings Total 175 minutes

Applications of Prediction-Based Decision Making 10 minutes
Case Study: Data Dictionary 10 minutes
SAS Viya Applications Menu 10 minutes
SAS Drive 15 minutes
SAS Viya Tools for Data Preparation 10 minutes
Cross Validation for Small Data Sets 10 minutes
Selecting Variables on the Data Tab 10 minutes
Global Metadata 10 minutes
Managing Missing Values: Details 10 minutes
Imputation Methods in Model Studio 10 minutes
Automated Pipeline Creation 10 minutes
Pipeline Templates in Model Studio 10 minutes
Logistic Regression 10 minutes
SAS Cloud Analytic Services 10 minutes
SAS Viya: A Shift in Mindset 10 minutes
Data Sources and CAS 10 minutes
Interfaces and Products 10 minutes

6 assignments Total 55 minutes

Question - Model Studio 5 minutes
Question - Data Partitions 5 minutes
Question - Missing Values 5 minutes
Question - Pipeline Templates 5 minutes
Question - Caslibs 5 minutes
Getting Started with Machine Learning and SAS Viya Review Quiz 30 minutes

3 app items Total 15 minutes

Practice - Creating a Project and Loading Data 5 minutes
Practice - Modifying the Data Partition 5 minutes
Practice - Building a Pipeline from a Basic Template 5 minutes

In this module, you learn to explore the data and finish preparing the data for analysis. You also learn some general considerations for selecting an algorithm.

What's included

14 videos12 readings7 assignments7 app items

14 videos Total 44 minutes

Introduction to Data Preprocessing and Algorithm Selection 1 minute
Exploring the Data 1 minute
Demo: Exploring the Data 5 minutes
Replacing Incorrect Values 1 minute
Demo: Replacing Incorrect Values Starting on the Data Tab 6 minutes
Feature Extraction 0 minutes
Text Mining 2 minutes
Demo: Adding Text Mining Features 6 minutes
Using Transformations to Handle Extreme or Unusual Values 4 minutes
Demo: Transforming Inputs 5 minutes
Selecting Useful Inputs 4 minutes
Demo: Selecting Features 6 minutes
Demo: Saving a Pipeline to the Exchange 2 minutes
Starting the Discovery Phase of the Analytics Life Cycle 1 minute

12 readings Total 120 minutes

Data Preprocessing Nodes in Model Studio 10 minutes
Risk Modeling Add-on for SAS Viya 10 minutes
Replacing Incorrect Values Starting with the Manage Variables Node 10 minutes
Singular Value Decomposition and the Text Mining Node 10 minutes
Feature Extraction Node 10 minutes
Transformations in Model Studio 10 minutes
Feature Selection and the Variable Selection Node: Details 10 minutes
Best Practices for Common Data Preparation Challenges 10 minutes
Feature Engineering in SAS Viya 10 minutes
Supervised Learning Algorithms in Model Studio 10 minutes
Considerations for Selecting an Algorithm 10 minutes
Comparison of Modeling Algorithms 10 minutes

7 assignments Total 60 minutes

Question - Data Exploration Node 5 minutes
Question - Text Mining Node 5 minutes
Question - Transformations 5 minutes
Question - Variable Selection Node 5 minutes
Question - Data Collection Challenges 5 minutes
Question - Algorithm Selection 5 minutes
Data Preprocessing and Algorithm Selection Review Quiz 30 minutes

7 app items Total 65 minutes

Practice - Exploring the Data 5 minutes
Practice - Replacing Incorrect Values Starting on the Data Tab 5 minutes
Practice - Adding Text Mining Features 5 minutes
Practice - Transforming Inputs 5 minutes
Practice - Selecting Features 5 minutes
Practice - Saving a Pipeline to the Exchange 20 minutes
Practice - Saving a Pipeline to the Exchange 20 minutes

In this module, you learn to build decision tree models as well as models based on ensembles, or combinations, of decision trees.

What's included

23 videos17 readings11 assignments7 app items

23 videos Total 71 minutes

Introduction to Decision Trees and Ensembles of Trees 1 minute
Basics of Decision Trees 3 minutes
Demo: Building a Decision Tree Model Using the Default Settings 9 minutes
Decision Trees for Categorical Targets: Classification Trees 4 minutes
Decision Trees for Interval Targets: Regression Trees 2 minutes
Improving the Decision Tree Model 0 minutes
Demo: Modifying the Structure Parameters 2 minutes
Recursive Partitioning 3 minutes
Splitting Criteria 4 minutes
Split Search 10 minutes
Demo: Modifying the Recursive Partitioning Parameters 1 minute
Optimizing the Complexity of a Decision Tree Model 1 minute
Pruning 3 minutes
Demo: Modifying the Pruning Parameters 2 minutes
Regularizing and Tuning the Hyperparameters of a Machine Learning Model 3 minutes
Building Ensemble Models 1 minute
Perturb and Combine Methods 6 minutes
Bagging 2 minutes
Boosting 1 minute
Comparison of Tree-Based Models 1 minute
Demo: Building a Gradient Boosting Model 4 minutes
Forest Models 3 minutes
Demo: Building a Forest Model 4 minutes

17 readings Total 170 minutes

Supervised Learning Node Results Window 10 minutes
Score Code in Model Studio 10 minutes
Interactively Edit a Decision Tree 10 minutes
Impurity Reduction Measures for Categorical and Interval Targets 10 minutes
Splitting Criteria in Model Studio 10 minutes
Adjustments in a Split Search 10 minutes
Missing Values in Decision Trees in Model Studio 10 minutes
Surrogate Splits 10 minutes
Calculating Variable Importance for Surrogate Splits 10 minutes
Bottom-Up Pruning Requirements 10 minutes
Pruning Options in Model Studio 10 minutes
Hyperparameter Optimization Approaches 10 minutes
Autotuning Options for Decision Trees in Model Studio 10 minutes
Use the Best Hyperparameter Values for a Model 10 minutes
Gradient Boosting Models 10 minutes
Autotuning Options for Gradient Boosting in Model Studio 10 minutes
Autotuning Options for Forests in Model Studio 10 minutes

11 assignments Total 80 minutes

Question - Decision Tree Nodes 5 minutes
Question - Decision Tree Splits 5 minutes
Question - Decision Trees 5 minutes
Question - Leaf Purity 5 minutes
Question - Number of Splits 5 minutes
Think about it 5 minutes
Question - Pruning 5 minutes
Question - Perturb and Combine Methods 5 minutes
Question Tree-Based Models 5 minutes
Question - Gradient Boosting versus Forest Models 5 minutes
Decision Trees and Ensembles of Trees Review Quiz 30 minutes

7 app items Total 140 minutes

Practice - Building a Decision Tree Using the Default Settings 20 minutes
Practice - Modifying the Structure Parameters 20 minutes
Practice - Modifying the Recursive Partitioning Parameters 20 minutes
Practice - Modifying the Pruning Parameters 20 minutes
Practice - Modifying the Pruning Parameters 20 minutes
Practice - Building a Gradient Boosting Model 20 minutes
Practice - Building a Forest Model 20 minutes

In this module, you learn to build neural network models.

What's included

19 videos11 readings6 assignments3 app items

19 videos Total 42 minutes

Introduction to Neural Networks 0 minutes
Beyond Traditional Regression: Neural Networks 4 minutes
Overcoming the Limitations of Neural Networks 3 minutes
Basics of Neural Networks 4 minutes
Estimating Weights and Making Predictions 3 minutes
Learning Process 2 minutes
Essential Discovery Tasks for Neural Networks 0 minutes
Demo: Building a Neural Network Using the Default Settings 3 minutes
Improving the Neural Network Model 0 minutes
Neural Network Architectures 4 minutes
Activation Functions 2 minutes
Shaping the Sigmoid 2 minutes
Demo: Modifying the Neural Network Architecture 2 minutes
Optimizing the Complexity of a Neural Network Model 1 minute
Weight Decay 3 minutes
Early Stopping 3 minutes
Regularizing and Tuning the Hyperparameters of a Neural Network Model 1 minute
Network Learning Hyperparameters 3 minutes
Demo: Modifying the Learning and Optimization Parameters 2 minutes

11 readings Total 110 minutes

Standardization Methods 10 minutes
Iterative Updating in Numerical Optimization 10 minutes
Numerical Optimization Methods in Model Studio 10 minutes
Deviance Measures in Model Studio 10 minutes
Stationary Versus Nonstationary Data 10 minutes
Calculating the Number of Parameters 10 minutes
Deep Learning 10 minutes
Hidden Layer Activation Functions in Model Studio 10 minutes
Target Layer Activation Functions and Error Functions in Model Studio 10 minutes
Important Hyperparameters for Neural Networks: Summary 10 minutes
Autotuning Options for Neural Networks in Model Studio 10 minutes

6 assignments Total 65 minutes

Question - Universal Approximators 5 minutes
Question - Parameter and Intercept Estimates 10 minutes
Question - Optimization Methods 5 minutes
Question - Deep Learning Models 5 minutes
Question - Model Generalization and Early Stopping 10 minutes
Neural Networks Review Quiz 30 minutes

3 app items Total 60 minutes

Practice - Building a Neural Network Using the Default Settings 20 minutes
Practice - Modifying the Neural Network Architecture 20 minutes
Practice - Modifying the Learning and Optimization Parameters 20 minutes

In this module, you learn to build support vector machine models.

What's included

17 videos7 readings5 assignments4 app items

17 videos Total 32 minutes

Introduction to Support Vector Machines 1 minute
Support Vector Machines as Classifier Models 2 minutes
Mathematical Definition of a Support Vector Machine 2 minutes
Maximum-Margin Hyperplane and Support Vectors 2 minutes
Essential Discovery Tasks for Support Vector Machines 0 minutes
Demo: Building a Support Vector Machine Using the Default Settings 3 minutes
Improving the Support Vector Machine Model 1 minute
Optimization Problem 1 minute
Accounting for Errors with Nonlinearly Separable Data 1 minute
Demo: Modifying the Methods of Solution Parameters 1 minute
Optimizing the Complexity of the Support Vector Machine Model 0 minutes
Feature Space Approach for Nonlinearly Separable Data 1 minute
Kernel Trick 2 minutes
Demo: Increasing the Flexibility of the Support Vector Machine 2 minutes
Model Interpretability 1 minute
Demo: Adding Model Interpretability 11 minutes
Regularizing and Tuning the Hyperparameters of the Support Vector Machine Model 0 minutes

7 readings Total 70 minutes

Dot Products 10 minutes
Constraints for Optimization 10 minutes
Number of Support Vectors 10 minutes
Lagrange Approach for Estimation 10 minutes
SVM Properties Related to Kernels and Training Algorithms 10 minutes
Model Interpretability Plots 10 minutes
Autotuning Options for Support Vector Machines in Model Studio 10 minutes

5 assignments Total 50 minutes

Question - SVM and the Curse of Dimensionality 5 minutes
Question - Non-linearly Separable Data 5 minutes
Question - Kernel Functions 5 minutes
Question - Model Interpretability 5 minutes
Support Vector Machines Review Quiz 30 minutes

4 app items Total 80 minutes

Practice - Building a Support Vector Machine Using the Default Settings 20 minutes
Practice - Modifying the Methods of Solution Parameters 20 minutes
Practice - Increasing the Flexibility of the Support Vector Machine 20 minutes
Practice - Adding Model Interpretability 20 minutes

In this module, you learn how to select the model that best meets the requirements of your business challenge and put the model into production. You also learn about managing the model over time.