Insights (Discover) - Best Practices

Ramya Priya Updated by Ramya Priya

In the world of data analytics, insights are crucial for businesses to understand the key factors driving their success. In Tellius, insights can be derived through machine learning or statistical inference techniques, providing a better understanding of the data. These insights can be categorized into key drivers, trends, comparisons, and anomalies/correlations.

Best Practices

  1. Understand the granularity of the data as it determines the insights that you will get as a result. Ensure that the data is properly aggregated to understand the key characteristics of certain types of invoices or transactions.
  2. Utilize the insights generation feature from search visualizations or vizpads that help explore the “why” from ad-hoc questions. Selecting anomalies provides the “Understand Why” option, which is a one-click trend insight that uses all features. Use the “Configure Your Insight” option to customize the feature list, filters, and time periods.
  3. Utilize the insights configuration from the Discover tab. This allows a more “hypothesis” driven approach to answering questions.
  4. Name Insights to match the outcome. A more user-friendly name helps keep track of insights over time. It is recommended to exclude unnecessary or useless features from the insights to speed up the generation process. This includes date columns, ID columns, and other irrelevant metrics.
  5. Use the edit option for pre-existing Insights. This allows quick iteration through insights by including or excluding more features, changing time periods, or filters from the original insight rather than reconfiguring from scratch each time.
  6. Save/move Insights into Projects, which is an effective way to organize content that can easily be shared with users or user groups.

Did we help you?

Vizpads (Explore) - Best Practices

Predict - Best Practices

Contact