Correlation analysis

Correlation analysis

Correlation Analysis in Lumenore offers valuable insights into the strength of relationships between selected Key Performance Indicators (KPIs) from your data. This statistical method gauges the degree of association between two or more variables, helping uncover how changes in one variable relate to changes in another. Consider the scenario where you aim to determine the variable relationship between discount and profit within a retail store dataset. Before initiating the configuration for correlation analysis, it’s crucial to contemplate the context, typically the Key Performance Indicators (KPIs) for which you seek correlation, and then proceed with the remaining process.

To conduct correlation analysis effectively, it is imperative to possess a dataset comprising a minimum of two Key Performance Indicators (KPIs) or metrics (e.g., Revenue, Cost, Discount, etc.) and associated dimensions (e.g., Agent, Customer Segment, or Product) to distribute the data accurately. This arrangement allows for a comprehensive assessment of the relationship between the chosen metrics through the correlation coefficient.

Key Concepts:

• Correlation Coefficient: A numerical value ranging from -1 to 1, indicating the strength and direction of the correlation.
• Perfect Positive Correlation: Coefficient of 1, signifying both variables increase together.
• Perfect Negative Correlation: Coefficient of -1, indicating one variable increases as the other decreases.
• Zero Correlation: Coefficient of 0, suggesting no association between variables.

Steps to perform correlation analysis in Lumenore:

Step 1: After accessing “Do You Know,” select “Correlation.”

Step 2: Choose a Schema and click “Next.”

Note: Ensure the criteria for correlation analysis (A KPI, Date, and Attribute) are met.

Step 3: Select the following to configure:

• Select correlation metrics: Choose at least two metrics or KPIs for analysis.
• Select data distribution attribute: Specify an attribute for data distribution (e.g., Date, Agent, Product).
• Select correlation attribute/group: Choose an attribute for correlation plots (e.g., Product Category, Country, Region).
• Remove outliers: Remove outliers from the selected KPIs if required.
• Do you want to add filters? Optionally add filters.

Click “Next.”

Step 4: Customize the insights narration to define the variables used. Then, click on “Save.”

Step 5: Name the insight for future access (default suggestion provided) and save it.

Note: If you wish to apply a filter, a window for creating filters will appear. As shown in the Trend Analysis, establish filters by groups or conditions as needed.

Step 6: A new window appears; click “Execute Now” to generate insights.

Upon initiation of execution, the system will undergo four background processes. You can also terminate the execution at any point before its completion.

For clarity, data insight for correlation analysis has been created using profit, sales, and quantity (correlation metrics), product (data distribution attribute), and country (correlation attribute/group). The dark-colored box shows a high correlation, and the light-colored box shows a low correlation.