AI-generated exploration analysis (Cloud only)

A new Exploration analysis report feature uses AI to generate an analysis of a selected view in the form of a PDF report. The generated report includes an executive summary followed by an impact analysis and outlier analysis for the exploration, allowing you to take faster business decisions.

The initial release of Exploration analysis report feature is available only in Planning Analytics Workspace Cloud and in English only.

Important: The Exploration analysis report feature is part of the Planning Analytics AI assistant add-on, which requires a separate license purchase; it is not included in a standard Planning Analytics Workspace license. To purchase a license, contact your IBM® sales representative or go directly to your IBM account.

To start an exploration analysis, follow these steps:

  1. Select an exploration in a book.
  2. In the toolbar, click AI operations and select Exploration analysis report.
  3. After the report is generated, a notification displays from which you can open the PDF file.

The exploration analysis is run on the first 120 rows and columns of the exploration.

When you run an Exploration analysis report, an impact analysis and outlier analysis is performed on the exploration.

The impact analysis determines the impact of data fields on each other as well as identifies and quantifies relationships across the data. Generative AI interprets and summarizes the analysis to describe the direct and indirect impact of the data fields on each other, as well as any dependencies and relationships between them.

An outlier analysis on the exploration identifies data points that deviate significantly from the norm, potentially indicating errors or anomalies. AI-generated insights are available for any outliers that were detected, helping you to investigate anomalies and improve the quality of your data.

AI-generated summary

The Exploration analysis report feature uses granite-3-8b-instruct from the Granite family of IBM foundation models to generate the executive summary and insights from the impact and outlier analysis.

The Granite models are decoder-only models that can efficiently predict and generate language. These models were built with trusted data that has the following characteristics:
  • Sourced from quality data sets in domains such as finance (SEC Filings), law (Free Law), technology (Stack Exchange), science (arXiv, DeepMind Mathematics), literature (Project Gutenberg (PG-19)), and more.
  • Compliant with rigorous IBM data clearance and governance standards.
  • Scrubbed of hate, abuse, and profanity, data duplication, and blocklisted URLs, among other things.
Note: IBM is committed to building AI that is open, trusted, targeted, and empowering. For more information about contractual protections that are related to IBM indemnification, see the IBM Client Relationship Agreement and IBM watsonx.ai service description.

Tips on working with AI

While working with Exploration analysis report, here are few things that you can do that might lead the AI model to generate a better analysis:

  • Ensure that the values in the exploration data are numeric.
  • Remove spacers from rows or columns.
  • Remove duplicate values.