Before you Begin
This 10-minute tutorial shows you how to automatically generate insights from your data using the Explain machine learning capability in Oracle Analytics.
Background
The machine learning Explain algorithm generates data insights and patterns about the selected data element in the context of the whole dataset.
Selecting Explain generates visualizations that describe basic facts, key drivers of the column values, segments (hidden groupings), and anomalies. Segments are leaf nodes containing data classification rules for the node's data value in the data that correlate and predict outcome values for the selected attribute. Anomalies are outliers or unexpected results for the data model used to Explain the attribute column. The Explain-Anomalies algorithm is not the same algorithm used for Advanced Analytics Outliers.
What Do You Need?
- Access to Oracle Analytics Cloud or Oracle Analytics Desktop
- Download terminations_workers_details.xlsx to your computer
Add the Dataset and Prepare the Data
Before using the Explain algorithm, you can review the data profiling results in the Prepare page, and implement changes to standardize the data.
- Sign in to Oracle Analytics.
When using Oracle Analytics Desktop, you must install machine learning (DVML) to use Diagnostics Analytics (Explain), Machine Learning Studio, or advanced analytics.
- On the Home page, click Create, and then click Dataset.
- In Create Dataset, click Drop data file here or click to browse, select the
terminations_workers_details.xlsx
file, and then click Open. - In Create Dataset Table from terminations_workers_details.xlsx, click OK.
- Click the terminations_workers_details tab. Select the Tenure in Months column, click Measure
, and then click Attribute.
- In Tenure in Months properties, click Number Format
. In the Number Format row, click Auto, and then select Number. In the Decimal Places row, click 2, and then select 1.
- Select the Terminations Week column, click Measure
, and then select Attribute.
- Click Save
. In Save Dataset As, enter
terminations_workers_details
in Name, and then click OK.Description of the illustration quality_insights.png
Visualize the Data
In this section, you select the basic facts generated by the Explain machine learning algorithm. You can also view the key drivers, segments, and anomalies for the termination type column.
Oracle Analytics enables Auto Insights as the default behavior.
- In the terminations_workers_details dataset, click Create Workbook.
- Close the Auto Insights panel.
- In the Data pane, right-click Termination Type, and then select Explain Termination Type.
Description of the illustration explain_term_type.png - In Explain Termination Type, hover your cursor over the upper right side of the canvas, and then click Select for Canvas
. When the check mark
changes to green, click Add Selected.
- In the Data pane, right-click Termination Type, select Explain. In Explain Termination Type, click Key Drivers of Termination Type.
You could select the visualizations generated for key drivers of termination type data to explore the data further. These visualizations aren't used in this tutorial.
Description of the illustration key_driver_vizs.png - Click X to close Explain Termination Type.
- Click Save, and select Save As. In Save Workbook, enter
HR Attrition
in the Name field, and then click Save.
Explain Resignations
In this section, you analyze resignations to uncover the reason why employees voluntarily resign. You also identify the departments that had the most resignations.
- In the visualization, hover your cursor over Resigned, right-click and select Keep Selected.
- From the Data pane, select Termination Reason, and then drag it to the canvas. Select Termination Reason, drag it to Color to switch places with Termination Type.
- Click Properties
. In the Title row, click Auto, select Custom, and then enter
Resignation Reason
as the title of the visualization.Description of the illustration term_type_term_reason.png - In the Data pane, hold down the Ctrl key and select the following:
- Termination Department
- Termination Reason
- # of Terminations
- Right-click, select Pick Visualization, and then select Horizontal Stacked
.
- Click the visualization Menu
, select Sort by, select # of Terminations, and then select High to Low.
- Click Properties
, click Auto in the Title row, and then select Custom. In Title, enter
Resignations by Dept and Reason
. - Click Save
.
Description of the illustration resignations.png
Analyze Trends in Resignations
In this section, you complete the picture of the termination data.
- In the Data pane, hold-down the Ctrl key, select Termination Week and # of Terminations. Right-click, select Pick Visualization, and then select Line
.
Description of the illustration term_count_by_week.png - In the line visualization, hover over the line, right-click and select Add Statistics, and then select Add Trend Line.
Description of the illustration trendline.png - In Properties
. In the Title row, click Auto and select Custom. In Title, enter
Terminations by Week Trend
. - Click Note
and select Add Note. In the Note field, enter
Career progression is the primary reason for resignations.
Click Save.Description of the illustration hr_attrition_analysis.png
Create a Presentation
In this section, you create the view your users see when the workbook is opened.
- Click Present. From Canvases, drag Explain Termination Type to Drag a Canvas Here to Begin.
- In the Explain Termination Type canvas, click the menu
, and then select Rename Page.
- In the Page Title field, enter
Attrition Reasons
. - Click Active Canvas. In the Filter Bar group, remove the check for Termination Type.
- Click Save.
- Click Preview
.
Description of the illustration attrition_reasons.png - Click Edit
return to the Present page.
Learn More
- Analyze Data with Explain in Oracle Analytics Cloud
Analyze Data with Explain in Oracle Analytics
E99266-09
July 2023
Copyright © 2023, Oracle and/or its affiliates.
Learn how to analyze data using Explain machine learning in Oracle Analytics.
This software and related documentation are provided under a license agreement containing restrictions on use and disclosure and are protected by intellectual property laws. Except as expressly permitted in your license agreement or allowed by law, you may not use, copy, reproduce, translate, broadcast, modify, license, transmit, distribute, exhibit, perform, publish, or display any part, in any form, or by any means. Reverse engineering, disassembly, or decompilation of this software, unless required by law for interoperability, is prohibited.
If this is software or related documentation that is delivered to the U.S. Government or anyone licensing it on behalf of the U.S. Government, then the following notice is applicable:
U.S. GOVERNMENT END USERS: Oracle programs (including any operating system, integrated software, any programs embedded, installed or activated on delivered hardware, and modifications of such programs) and Oracle computer documentation or other Oracle data delivered to or accessed by U.S. Government end users are "commercial computer software" or "commercial computer software documentation" pursuant to the applicable Federal Acquisition Regulation and agency-specific supplemental regulations. As such, the use, reproduction, duplication, release, display, disclosure, modification, preparation of derivative works, and/or adaptation of i) Oracle programs (including any operating system, integrated software, any programs embedded, installed or activated on delivered hardware, and modifications of such programs), ii) Oracle computer documentation and/or iii) other Oracle data, is subject to the rights and limitations specified in the license contained in the applicable contract. The terms governing the U.S. Government's use of Oracle cloud services are defined by the applicable contract for such services. No other rights are granted to the U.S. Government.
This software or hardware is developed for general use in a variety of information management applications. It is not developed or intended for use in any inherently dangerous applications, including applications that may create a risk of personal injury. If you use this software or hardware in dangerous applications, then you shall be responsible to take all appropriate fail-safe, backup, redundancy, and other measures to ensure its safe use. Oracle Corporation and its affiliates disclaim any liability for any damages caused by use of this software or hardware in dangerous applications.
Oracle and Java are registered trademarks of Oracle and/or its affiliates. Other names may be trademarks of their respective owners.
Intel and Intel Inside are trademarks or registered trademarks of Intel Corporation. All SPARC trademarks are used under license and are trademarks or registered trademarks of SPARC International, Inc. AMD, Epyc, and the AMD logo are trademarks or registered trademarks of Advanced Micro Devices. UNIX is a registered trademark of The Open Group.
This software or hardware and documentation may provide access to or information about content, products, and services from third parties. Oracle Corporation and its affiliates are not responsible for and expressly disclaim all warranties of any kind with respect to third-party content, products, and services unless otherwise set forth in an applicable agreement between you and Oracle. Oracle Corporation and its affiliates will not be responsible for any loss, costs, or damages incurred due to your access to or use of third-party content, products, or services, except as set forth in an applicable agreement between you and Oracle.