Predictive Analytics using Oracle Data Mining (D91316)

Introduction

• Course Objectives
• Suggested Course Prerequisites
• Suggested Course Schedule
• Class Sample Schemas
• Practice and Solutions Structure
• Review location of additional resources

Predictive Analytics and Data Mining Concepts

• What is the Predictive Analytics?
• Introducting the Oracle Advanced Analytics (OAA) Option?
• What is Data Mining?
• Why use Data Mining?
• Examples of Data Mining Applications
• Supervised Versus Unsupervised Learning
• Supported Data Mining Algorithms and Uses

Understanding the Data Mining Process

• Common Tasks in the Data Mining Process
• Introducing the SQL Developer interface

Introducing Oracle Data Miner 4.1

• Data mining with Oracle Database
• Setting up Oracle Data Miner
• Accessing the Data Miner GUI
• Identifying Data Miner interface components
• Examining Data Miner Nodes
• Previewing Data Miner Workflows

Using Classification Models

• Reviewing Classification Models
• Adding a Data Source to the Workflow
• Using the Data Source Wizard
• Using Explore and Graph Nodes
• Using the Column Filter Node
• Creating Classification Models
• Building the Models
• Examining Class Build Tabs

Using Regression Models

• Reviewing Regression Models
• Adding a Data Source to the Workflow
• Using the Data Source Wizard
• Performing Data Transformations
• Creating Regression Models
• Building the Models
• Comparing the Models
• Selecting a Model

Using Clustering Models

• Describing Algorithms used for Clustering Models
• Adding Data Sources to the Workflow
• Exploring Data for Patterns
• Defining and Building Clustering Models
• Comparing Model Results
• Selecting and Applying a Model
• Defining Output Format
• Examining Cluster Results

Performing Market Basket Analysis

• What is Market Basket Analysis?
• Reviewing Association Rules
• Creating a New Workflow
• Adding a Data Source to the Workflow
• Creating an Association Rules Model
• Defining Association Rules
• Building the Model
• Examining Test Results

Performing Anomaly Detection

• Reviewing the Model and Algorithm used for Anomaly Detection
• Adding Data Sources to the Workflow
• Creating the Model
• Building the Model
• Examining Test Results
• Applying the Model
• Evaluating Results

Mining Structured and Unstructured Data

• Dealing with Transactional Data
• Handling Aggregated (Nested) Data
• Joining and Filtering data
• Enabling mining of Text
• Examining Predictive Results

Using Predictive Queries

• What are Predictive Queries?
• Creating Predictive Queries
• Examining Predictive Results

Deploying Predictive models

• Requirements for deployment
• Deployment Options
• Examining Deployment Options