Before you Begin

This tutorial shows you how to configure insights to generate insights that display on the Insights dashboard. This tutorial takes approximately 40 minutes to complete.


IPM Insights analyzes past data and predicted data, helping you find patterns and insights into data that you might not have found on your own. Insights can be trends, anomalies, forecast bias, or variations. With IPM Insights, the insight discovery phase of the planning process is automated with data science and financial pattern recognition, enhancing your forecast effectiveness. Using IPM Insights, you can analyze and explore data across any account. IPM Insights automates processing large amounts of multidimensional data, so that as new actuals come into the system, you quickly detect patterns in your data or hidden correlations, streamlining reporting, improving your forecasting, and strengthening your decision making. You spend less time in analysis, saving time in the overall planning process.

Forecast Variance Insight

You configure IPM Insights by selecting the type of analysis to perform, specifying the slice definitions for analysis, configuring the analysis, and then defining the settings for the insights displayed on the Insights dashboard. You can define insights for as many data intersections as you need. Planners see insights only for slices of data to which they have access.

You can also define a prediction using Auto Predict to predict future performance based on historical data and schedule a job to run that prediction definition, automating the prediction process. You can use these prediction results as input for generating insights.

What Do You Need?

An EPM Cloud Service instance allows you to deploy and use one of the supported business processes. To deploy another business process, you must request another EPM Enterprise Cloud Service instance or remove the current business process.

You must have:

  • Service Administrator access to an EPM Enterprise Cloud Service instance.
  • Upload and import this snapshot into your instance.

Activating Navigation Flows

In this section, you activate the IPM Insights navigation flow so you can work with Insights.

  1. On the home page, click Tools, then Navigation Flows.
    home page
  2. For the IPM Insights row, under Active, click Inactive.
    Navigation Flow page

    The IPM Insights navigation flow is activated, and the Default flow is inactivated.

    Navigation Flow page
  3. Click Home (Home).
  4. Click Navigation Flow (Navigation Flow), and then IPM Insights.
    Navigation Flow

    The IPM Insights navigation flow is displayed.

    home page

  5. Tip:

    You can reload the navigation flow to ensure the IPM Insights navigation flow is displayed.
    Setting and Actions Menu

Exploring Insights

In this section, you explore Insights with a sample application for Vision. You analyze Revenue data for the Sales West entity and identify areas on which you need to focus in order to improve your forecasting for this entity. Insights can be set up for any data across any account or measure – revenue, expense, balance sheet, cash flow or volumes.

You start by reviewing the underlying data, both historical and future data for the Sales West entity.

  1. On the home page, click IPM, then Insights Data.
    Home page

  2. Historical data for Insights is displayed.

    Historical Data

    The Sales West entity has five Revenue accounts and seven Products.

    Revenue Accounts
    North Channel
    Consumer Channel

    Product X
    Sentinal Standard Notebook
    Sentinal Custom Notebook
    Envoy Standard Netbook
    Envoy Custom Netbook
    Other Computer
    Tablet Computer

    Data for historical actuals and historical forecasts is available starting from Jan FY19. The future forecasts have been made for the next six months (Jul FY21 through Dec FY21).

    Planners have tried their best to forecast revenue data for the Sales West entity across five revenue accounts and seven products. You will do the following:

    • Take a data-driven approach to analyzing historical data and identifying areas where significant forecast variance and/or bias exist
    • Leverage machine-generated predictions which incorporate past trends and patterns to more accurately forecast data for the next six months

    You will leverage IPM Insights to apply a data-driven approach to forecasting with data science.

Configuring Insights

In this section, you create an insight by selecting the types you want to create. Then you define the historical and future data slices, set thresholds, and define display dimensions and impact magnitude thresholds.

Creating Insights

  1. Above Historical data for Insights, click Configure
    Select Card
  2. Click Create.
    Insights page

    The Details page for IPM Configurator is displayed.

    IPM Configurator
  3. In Details, for Name enter Revenue Analysis for Sales West, and for description enter To analyze the revenue data by product and generate all three types of insights.
    Details page
  4. Under Generate Insights, select Forecast Variance & Bias Insights.
    Generate Insights

    Forecast variance and bias insights analyzes historical data to reveal hidden bias in forecasts submitted by planners. This type of insight measures the variance or bias between two historical scenarios such as Forecasts and Actuals. .

  5. Under Generate Insights, select Prediction Insights.
    Generate Insights

    Prediction insights look for variances between future scenarios such as forecasts and computer-generated predictions.

  6. Keep the default selection of No to indicate that you do not have prediction data available.
    Generate Insights


    If you have prediction data, you can indicate that by clicking the option to toggle it on. With no predicted data, Auto Predict is automatically selected under Generate Predictions.

    Auto Predict uses the historical data for the intersection you defined to generate prediction data that is used for the insight. Prediction results can be used as input for generating prediction insights.

  7. Under Generate Insights, select Anomaly Insights.
    Generate Insights

    Anomaly insights detect outlier values that vary widely from other values.

  8. Click Next.

Selecting the Historical Data Slice

In this section, you define the data slices used for insights analysis. For the Historical Data section, you define both actuals and the forecasts provided by planners. The slice definitions show all the dimensions for the cube, except for the Year and Period dimensions. All members start out with their root member selected.

  1. Under Historical Data, for Cube, select Plan 1 and for Number of Historical Years, enter 2.
    Historical Data
  2. Under Actual, click Account.
    Historical Data
  3. In Member Selector, search for Revenue, and click Function Selector (Function Selector).
    Select Members
  4. Select Level 0 Descendants.
    Member Relationships
  5. Click HSP_View, and select BaseData.
    Select Members
  6. Click Scenario, and select Actual.
    Select Members
  7. Click Version, and select Working.
    Select Members
  8. Click Entity, then search for and select the second Sales West entry.
    Select Members
  9. Click Product, and search for Computer Equipment.
    Select Members
  10. For Computer Equipment, click Function Selector (Function Selector), and select Level 0 Descendants.
    Member Relationship
  11. Click OK.
    Select Members
  12. Under Forecast, click the Actual scenario.
  13. In Member Selector, select Forecast and click OK.
    Select a Member

Selecting the Future Data Slice

For the Future Data section, you select the cube and then define the slice of data for the future data, both the forecast provided by planners and the base prediction (most likely a scenario).

  1. Under Future Data, for Forecast, click the Actual scenario.
    Future Data
  2. In Member Selector, select Forecast, and click OK.
    Select a Member
  3. Under Base Prediction, for Scenario, click Actual.
    Future Data
  4. In Member Selector, select Predict Base, and click OK.
    Select a Member
  5. Note:

    If data is available, you can add a Best Case and Worst Case definition and define the slice of data for the best case and worst case scenarios.
  6. Click Future Period to select Future Periods.
    Future Data
  7. Under Period, click Select Period.
    Select Period
  8. In Member Selector, for Period, select Jul.
    Select a Member
  9. Click Year, select FY21, and click OK.
    Select a Member


    When you select Auto Predict, your prediction results are stored in this location.
  10. Click Next.
    Defining Slice

Defining Thresholds

You define the error tolerance and thresholds for insights. IPM Configurator selects default metrics for analysis.

  1. For Forecast Variance & Bias Insights, for Error Tolerance Limit, keep the selected error tolerance limit of 5%.
    Error Tolerance Limit

    The error tolerance percentage defines the percentage variance between historical forecasts submitted by planners and actuals that lies within acceptable range. If the percentage variation crosses the error tolerance limit, it is considered for bias calculation.

  2. For Prediction Insights, change the threshold to 25%.
    Prediction Threshold

    The Prediction threshold defines the acceptable percentage variance between future forecasts submitted by planners and computer-generated predictions.

  3. For Anomaly Insights, accept the Threshold of 3%.
    Anomaly Threshold

    The Anomaly threshold defines the acceptable threshold for Z-score value (the standard deviation from the mean of the values). Anything that is too far from zero (the threshold is usually a Z-score of 3 or -3) should be considered an outlier. An insight is generated when the specified outlier detection metric crosses the specified threshold.

Defining Metrics

You define metrics and trigger criteria on the Advanced Options page. Forecast variance indicates the level of accuracy of the forecasts submitted by planners. Forecast bias indicates the tendency of the direction of forecast error. A tendency to forecast in excess of the actuals is considered an “over-forecasting bias,” while a tendency to forecast below the actuals is considered an “under-forecasting bias.” For prediction insights, you specify how the deviation (variance) is determined by specifying the metric and threshold to measure the variance between future forecasts and historical predictions.

  1. Click Show Advanced Options.
    Show Advanced Options
  2. For Forecast Variance & Bias Insights, select the deviation percentage at which to trigger an insight. Change the Threshold to 25%.
    Deviation Metric
  3. Specify the metric to use to measure forecast bias. For Bias Metric, set the threshold to 50%.

    An insight is generated when either deviation or bias crosses the specified threshold.

  4. Select the deviation percentage between the future forecasts submitted by planners and computer-generated predictions at which to trigger an insight. For Prediction Insights, set the threshold to 50%.
    Prediction Threshold
  5. For Anomaly Insights, keep the selected threshold of 3%.
    Anomaly Insights Theshold

    The threshold for Anomaly insights sets the threshold at which to trigger an insight.

  6. Tip:

    For help on any of the metrics, click Help (Help).
  7. Click Next.

Setting Display Dimensions and Impact Magnitude Thresholds

On the Settings page, you configure the settings that define how to display the insights to planners. You select the dimensions that planners will use to navigate and analyze the insights. The dimensions you select will display on the Insights dashboard. You also define the impact magnitude thresholds to categorize insights into High, Medium, and Low groups.

  1. Under Display Dimensions, select Account, Entity, and Product.
    Display Dimensions
  2. For Impact Magnitude Thresholds, change the low threshold to 30% and the High threshold to 60%.
    Impact Magnitude Thresholds

    When insights are displayed on the Insights dashboard, this setting categorizes insights into High, Medium, and Low groups based on the percentage impact calculated for each insight. This helps users focus attention on the insights that have more extreme variations.

  3. Click Save.


    Insight definitions are saved as global artifacts (in the Auto Predict folder under Global Artifacts) and are backed up with the maintenance snapshot.
  4. Click Cancel.
    IPM Configurator

    The Configured insight is displayed.

    Confgure Insights

Specifying Insight Priority

In this section, you review the priority set for specific accounts.

  1. Click Navigator (Navigator) and under Application, click Overview.
    Navigator Menu
  2. Click Dimensions.
    Application Overview
  3. Click Account.
  4. Click Zoom in Bottom Level (Zoom in Bottom Level).
    Account Dimension
  5. Select the North Channel row and scroll to the right until you see the Priority column.
    Account Dimension

    The priority for each revenue account is displayed. North Channel has a high priority. Consumer Channel has a medium priority.

    Account Dimension Priority
  6. Note:

    The relative priority of accounts is considered when ranking or prioritizing the generated insights. The magnitude of impact and the relative importance are the two factors considered for the prioritization of insights.
  7. Click Cancel.

Learn More