Skip to Main Content

Breadcrumb for learning path

Main Parent

Learning Path Details Parent

bubbles_banner

Information

learning_path_info

Get Started with Oracle Data Miner User Interface

You can solve business problems by mining data stored in your database using Oracle Data Miner 19.4 and your Oracle Database 19c instance. This set of tutorials provide a set of the key job tasks performed using Oracle Data Miner, including text mining, applying logistic regression models, using predictive queries and mining JSON data. The tutorials leverage the data provided by the Oracle Sales History (sh) sample schema.

Enroll the User-Public

Learning_path_filler

Learning_path_icons

inetrmediate Intermediate
duration 165 Min
modules 8 Modules

Learning Path Contents

Module Sections Topics and more

  • Before You Begin
      duration 0 Min
     
    Hide
    About this learning path
    • The tutorials in this learning path were created using Oracle SQL Developer version 19.3 and Oracle Database Production 19.3.0.0.0. Oracle Machine Learning User Interface (Data Miner) 18.4 is included with Oracle SQL Developer. You may use an older (or newer version) of Oracle Database, Oracle SQL Developer and Oracle Data Miner, however, just note that your results and the screenshots may not match exactly.

  • Set up a Data Miner Instance
      duration 0 Min
     
    Hide
    • The Oracle Machine Learning User Interface (Data Miner) graphical user interface (GUI) is included as a free extension of Oracle SQL Developer. In order to use the Oracle Data Miner GUI to perform data mining, you must complete the following three setup tasks:

      1. Create a database user account for data mining
      2. Create a database connection within SQL Developer for the data miner user
      3. Install the Oracle Data Miner Repository

      Note: You do not need any experience with SQL Developer in order to perform the required steps.

  • Using Oracle Data Miner
      duration 45 Min
     
    Hide
    • This lesson focuses on a business problem that can be solved by applying a Classification model. In our scenario, ABC Company wants to identify customers who are most likely to purchase insurance.

      Note: For the purposes of this tutorial, the "Data and Acquisition" phase has already been completed, and the sample data set contains all required data fields. Therefore, this lesson focuses primarily on the "Building and Evaluation of Models" phase.

  • Apply Text Mining with an EM Clustering Model
      duration 30 Min
     
    Hide
    • This lesson focuses on a text mining problem that can be solved by applying a Clustering model using the EM algorithm. In our scenario, ABC Company wants to use the data from customer feedback to predict the kind of group (or cluster) to which a customer tends to belong.

      To accomplish this goal, you build a workflow that:

      • Combines text, demographic, and customer profile data
      • Uses a Clustering model against the source data
      • Specifies the EM algorithm, and enables text mining options within the clustering model
      • Generates predictive results from the text data
  • Use Logistic Regression Models (GLM) to Predict Customer Affinity
      duration 30 Min
     
    Hide
    • In this lesson, you focus on a business problem that can be solved by applying a Classification model. In our scenario, ABC Company wants to know which customer attributes are most significant in predicting the gender of a customer. The new feature selection / generation enhancements are used as part of this mining exercise.

      In this new workflow, you:

      • Identify and select two new data sources from the Oracle Database sample SH schema: the SALES and CUSTOMERS tables.
      • Summarize the QUANTITY_SOLD and AMOUNT_SOLD measures from the SALES table by Customer and Product, over the Promotion and Channel dimensions.
      • Place the summarized data into a new table.
      • Join the summarized sales data with customer data to provide a pool of data for the Classification model.
      • Apply the Feature Selection / Generation option with a GLM algorithm and examine the results.
  • Use Predictive Queries with Oracle Data Miner
      duration 30 Min
     
    Hide
    • Data mining can be used to solve many kinds of predictive analysis problems, including the following:

      • Predicting outcomes or values (Classification or Regression models)
      • Finding natural segments or clusters in a population (Clustering models)
      • Finding fraudulent or rare events (Anomaly Detection models)
      • Creating new attributes (features) for a target variable by combining original attributes (Feature Extraction models)

      Oracle Data Miner provides predictive query capabilities for these specific model types. The predictive query options enable dynamic scoring of these model by generating a transient model that is not persisted.

  • Mine JSON Data Using Oracle Data Miner
      duration 30 Min
     
    Hide
    • In this lesson, you create a workflow that imports JSON data by using the JSON Query node. The JSON Query node enables you to selectively query desirable attributes and project the result in relational format. Once the data is in relational format, you can treat it as a normal relational data source and start analyzing and mining it immediately.

      In the workflow, you:

      • Identify the JSON data
      • Specify the desirable attributes for query purposes
      • Examine the JSON data using the JSON Query node
      • Build Classification models to provide predictive analysis on the JSON data