Considerations for IPM Insights
The following are some of the considerations for IPM Insights and Auto Predict.
Considerations:
- IPM Insights requires an EPM Enterprise Subscription.
- IPM Insights works with these business processes:
- Planning. IPM Insights works
with these Planning
application types:
- Custom
- Modules
- FreeForm
- Sales Planning
- Strategic Workforce Planning
- Cash Forecasting
- FreeForm.
-
Oracle Sales Planning Cloud and Oracle Strategic Workforce Planning Cloud.
- Enterprise Profitability and Cost Management.
- Tax Reporting.
- Financial Consolidation and Close.
- Planning. IPM Insights works
with these Planning
application types:
- IPM Insights works only with applications with Hybrid mode enabled.
-
IPM Insights honors both member level security and cell level security, so planners see insights only for slices of data to which they have access. However, note that insights are not generated for a user when cell level security is defined on Year/Period dimensions.
- If you add dimensions to the application after the job is created, you must reconfigure the IPM job to include the additional dimensions.
- Note the following considerations for the Insights Generative AI summary feature:
- Insight summaries use GenAI. Output from GenAI may not always be factual, accurate, or appropriate. You are responsible for reviewing and using GenAI output at your discretion.
- The Insights Generative AI summary feature requires an EPM Enterprise Cloud service subscription.
- Narratives are generated in English only.
- Summaries are available for all insight types.
- Administrators need to re-run existing insights for users to be able to see the AI summary.
- The GenAI feature is available only for OCI environments, and it is not yet available in all OCI regions. To view the regions where it is available, refer to Availability of Generative AI in the Operations Guide.
IPM Insights Support Matrix
Review the table for a summary of the supported SKUs, business processes, and application types for IPM Insights.
Table 13-1 IPM Insights Support
SKU | Business Process | Application Type | Supported? | Comments |
---|---|---|---|---|
EPM Enterprise Subscription | Planning | Modules | Supported |
Hybrid Essbase must be enabled. |
Planning | Custom | Supported |
Hybrid Essbase must be enabled. |
|
Planning | Freeform | Supported |
Hybrid Essbase must be enabled. |
|
Planning | Sales Planning | Supported |
Hybrid Essbase must be enabled. |
|
Planning | Strategic Workforce Planning | Supported |
Hybrid Essbase must be enabled. |
|
Planning | Predictive Cash Forecasting | Supported |
Hybrid Essbase must be enabled. |
|
FreeForm | Supported |
Hybrid Essbase must be enabled. |
||
Enterprise Profitability and Cost Management | Supported | |||
Tax Reporting | Supported |
Hybrid Essbase must be enabled. |
||
Financial Consolidation and Close | Supported |
Hybrid Essbase must be enabled. |
||
Other business processes | Not supported | |||
Legacy SKU | Planning | Enterprise Planning and Budgeting Cloud | Not supported | |
Planning | Planning and Budgeting Cloud | Not supported | ||
Other business processes | Not supported | |||
EPM Standard Subscription | Planning | Standard Module | Not supported | |
Other business processes | Not supported | |||
Sales Planning | Planning | Sales Planning | Supported |
Hybrid Essbase must be enabled |
Strategic Workforce Planning | Planning | SWP | Supported |
Hybrid Essbase must be enabled |
Best practices:
- Historical Data: Prediction results are more accurate the more historical data you have. There should be at least twice the amount of historical data as the number of prediction periods. For example to predict 12 months in the future, you should have at least 24 months of historical data. At the time of prediction, if there is not enough historical data available, a warning is displayed.
- Time Granularity of Predictions: Because the lowest Period dimension member level in an Insights job determines the time granularity of the prediction, create the Insights job using the lowest level of Period members possible so that the greatest amount of historical data can be used.