3.1 Classification Use Case
A retail store has information about its customers' behavior and the purchases they make. Now with the available data, they want you to analyze and identify the type of customers most likely to be positive responders to an Affinity Card loyalty program. High Affinity Card responders are defined as those customers who, when given a loyalty or affinity card, hyper-respond, that is, increase purchases more than the Affinity Card program's offered discount. In our data set, a responder is designated with value 1, and a non-responder with value 0. In this use case, you will demonstrate how to identify such customers using the Support Vector Machine model.
Related Contents
| Topic | Link |
|---|---|
| OML4R GitHub Example | Classification Support Vector Machines (SVMs) |
| About Support Vector Machines (SVMs) | Classification Support Vector Machines (SVMs) |
| Shared Settings | Shared Settings |
Before you start your OML4R use case journey, ensure that you have the following:
- Data Set
The data set used for this use case is from the SH schema. The SH schema can be readily accessed in Oracle Autonomous Database. For on-premises databases, the schema is installed during the installation or can be manually installed by downloading the scripts.
- Database
Select or create database out of the following options:
- Get your FREE cloud account. Go to https://cloud.oracle.com/database and select Oracle Database Cloud Service (DBCS), or Oracle Autonomous Database. Create an account and create an instance. See Autonomous Database Quick Start Workshop.
- Download the latest version of Oracle Database (on premises).
- Machine Learning Tools
Depending on your database selection,
- Use OML Notebooks for Oracle Autonomous Database.
- Install and use Oracle SQL Developer connected to an on-premises database or DBCS. See Installing and Getting Started with SQL Developer.
- Other Requirements
Data Mining Privileges (this is automatically set for ADW). See System Privileges for Oracle Machine Learning for SQL.
- Load Data
You will be using the SUPPLEMENTARY_DEMOGRAPHICS data set available in the SH schema. Use theore.syncfunction to create anore.frameproxy object in R that represents a database table, view, or query. - Explore Data
Explore the data to understand and assess the quality of the data. At this stage assess the data to identify data types and noise in the data. Look for missing values and numeric outlier values. - Build Model
This model is designed to classify data into predefined categories by learning from training data. - Evaluate
Before you make predictions using your model on new data, you should first evaluate model accuracy. You can evaluate the model using different methods. - Deploy the Model
The machine learning model,SVM_CLASSIFICATION_MODEL, has been successfully trained and exists in your schema as a first-class database object. While you can use this model directly from R, for database applications, you can also run it directly from SQL queries.
Related Topics
Parent topic: Use Cases