Before you Begin

This 30 minute tutorial shows you how to run and schedule Insights in EPM Cloud. Before stepping through this tutorial, please review the Configuring Insights hands-on tutorial. The sections build on each other and should be completed sequentially.


Insights automate data analysis by finding patterns in data so you don’t have to. As new data is loaded into your EPM Cloud system, the Insight engine processes the data for key signals such as variance, trends, anomalies, and forecast bias. Instead of spending hours manually looking for patterns in your data, Insights does it for you. Insights surfaces just the patterns that are most relevant. You can configure the insights for materiality and importance.

The insights are delivered in an easy-to-use display. The list of insights are easily sorted and filtered. For example, you can easily filter on specific patterns within a threshold with just a few clicks. By delivering insights faster, it helps Finance get to more value-added activity – such as engaging with the business to solve problems.

Insights display

After consulting with business experts, administrators configure insights to define the insights that planners see on the Insights display. Configured Insights can then be run immediately or scheduled to run on a regular basis.

Insights use both historical and predicted data. There are three different types of insights:

  • Forecast variance and bias insights: reveal hidden bias in forecasts submitted by planners by analyzing historical forecasts and actual data. This type of insight measures the variance or bias between two historical scenarios such as Forecasts and Actuals.
    Forecast Variance Insight

  • Prediction insights: review where variances are greatest between future forecasts compared with machine predictions. For prediction insights, you need prediction data generated for future time periods. If prediction data is not available, you can automatically predict data using Auto Predict. You can bring in Machine Learning predictions or other predicted data to use for Prediction Insights.
    Prediction Insight

  • Anomaly insights: detect unusual patterns in data. This type of insight detects outlier values that vary widely from other values, for example, a sudden volatility in actuals due to an external or internal event.
    Anomaly Insight

In this tutorial, you run and schedule 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 click IPM Insights.
    Navigation Flow

    The IPM Insights Navigation Flow is displayed.

    home page

Reviewing Configured Insights

In this section, you review the configuration for Insights.

  1. On the home page, click IPM, then Configure.
    Home page

    Configured Insights are displayed.

    Configure Page
  2. In the row for Revenue Analysis for Sales West, click Actions (Actions) and select Edit.
    Configure Page

    This configuration runs a revenue analysis for Sales West to analyze revenue by product and generates forecast variance and bias insights, prediction insights, and anomaly insights. Auto Predict is used to predict future performance based on historical data using time series forecasting techniques.

    Types page
  3. Click Next.

    Both historical and future data are defined. For historical data, the cube, and number of historical years are specified and the slice of data for both the Actual and Forecast are defined.

    Historical Data

    Under Future Data, the cube and slice of data for the future data, both the forecast provided by planners, and the base prediction, most likely a scenario, are defined. Future Periods specifies what periods are included in the analysis for future data. Prediction results are stored in this location when you select Auto Predict.

    Future Data
  4. Click Next.

    For Forecast Variance and Bias Insights, the error tolerance percentage defines the percentage variance between historical forecasts submitted by planners and actuals that lies within an acceptable range. In this example, any difference of 5% or above between historical forecasts and historical actuals is considered a significant variance and triggers an insight.

    Error Tolerance from Actuals

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

    Prediction Threshold

    For Anomaly insights, the 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 is typically considered an outlier.

    z_Score Theshold
  5. Click Next.

    The Settings page shows the selected display dimensions for the Insights list and the impact magnitude thresholds.

    Settings page

    Display Dimensions are the dimensions that planners will use to navigate and analyze the insights. The selected dimensions display on the Insights display.

    Display Dimensions

    Impact Magnitude Thresholds define the low and high thresholds. When insights are displayed on the Insights display, this setting categorizes insights into High, Medium, and Low groups based on the percentage impact calculated for each insight. This helps focus attention on the insights that have more extreme variations.

    Impact Magnitude
  6. Click Cancel.

Running Insights from the Configure Page

In this section, you run Insights from the Insights Configure Page. Insights run as a job. After configuring insights, you can run them at any time. You can review the status of the job on the Jobs page.

Submitting Insights Jobs

  1. For Revenue Analysis for Sales West, under Actions, click Actions (Actions), and select Run.
    Configure Page

    When you run an insight, IPM Insights analyzes the data at each available intersection and looks for patterns and anomalies.

  2. At the information message, click OK.
    Job Submitted


    Insights are available on the Insights display for six months, after which they are purged the next time you run an IPM Insights job.

Reviewing Insights Jobs

You can review information about Insights jobs.

  1. Click Navigator (Navigator), and under Application, click Jobs.
    Navigator Menu
  2. On the Jobs page, to review the details about the job, click Revenue Analysis for Sales West.
    Jobs Page

    The associated subjobs that ran for this job are displayed.

    Job Components
  3. Next to Job Status, click Completed.

    Details about the job are displayed.

    Job Details
  4. Click Forecast Variance & Bias Insights.
    Components of Job

    Job Details are displayed. After analyzing thirty-five series for forecast variance and bias, two insights were generated.

    Job Details
  5. Click Back.
  6. Click Anomaly Insights.
    Components of Job

    Job Details are displayed. After analyzing thirty-five series for anomaly insights, two insights were generated.

    Job Details
  7. Click Back.
  8. Click Prediction Insights.
    Job Details

    Job details are displayed. After analyzing thirty-five series for prediction, three insights were generated.

    Job Details
  9. Click Close.

Scheduling Insights to Run

In this section you schedule Insights to run at a future time. You set up a job to run insights at regular intervals, for example, when you have a new set of actuals.

  1. On the Jobs page, click Schedule Jobs.
    Jobs Page
  2. On the left, under "What type of job is this?", scroll down and select Insights.
    Job Type
  3. Set up a monthly job. Set it to run on the 10th day of the month following today's date, similar to the following, and click Next.
    Schedule Job
  4. Review the job details and click Next.
    Job Details on Schedule Job
  5. Review the job selections, and click Finish.
    Review Scheduled Job Details

    The job is scheduled and is listed under Pending Jobs. You can edit or delete the scheduled job.

    Jobs Page

Learn More