Administrators are responsible for provisioning Brightspace Student Success System by:
- Managing target courses
- Building predictive models
- Monitoring active courses
Add a target course
- From the Admin Tools menu, click Student Success System.
- Click Add Course.
- Select the course you want to add.
- Click Add.
Configure a predictive model
Once you add a target course, you can configure a predictive model for it. While the model is being built, the progress status displays as "Building [ ]% complete." Click Refresh to refresh the building status or Cancel to cancel it. Once the build completes, the model status displays as "Ready" and the Mean Squared Error (MSE) displays. The MSE is also visible on the Review Model page for the predictive model.
MSE is calculated as the average deviations between the estimated grades used in calculating the success index and actual grades. The average is calculated over all weeks and all data domains. The value is then normalized to a percentage value. The smaller the MSE, the more accurate the predictive model is thought to be.
- From the Admin Tools menu, click Student Success System.
- From the context menu of the target course you want to configure, click Configure Model.
- Select the domains you want to include in the model. To eliminate irrelevant measurements from the model, D2L recommends excluding domains that have no corresponding data in the system.
Note: The Preparedness domain was part of a D2L beta program that is now closed; it is not a valid domain to include in predictive models.
- In the Advanced Model Options section (click the arrow to expand), select the Model Aggregation Type and Data Extraction preferences.
Note: The system selects the Domain Aggregation and Cumulative Weeks options by default. D2L recommends leaving the default selections in place.
- Confirm or modify the grade ranges for the three risk categories. You can set default values by modifying the d2l.Tools.S3.GradeRangePotentialRiskValue and d2l.Tools.S3.GradeRangeSuccessfulValue configuration variables.
- If start and end dates are not automatically included, enter a Start Date and End Date for the course.
- To define which roles to include in the predictive model, click the Edit icon.
- In the Map Historic Courses section, click Add Course to add at least one historic course to the predictive model.
Note: The more consistent the historic courses are with the target course you are configuring, the more accurate you can expect the predictions to be. Any historic course you add must contain enrolled participants.
- Click Save and Continue. If a course does not meet the requirements for use as a historic course in the predictive model, an Error icon displays in the Status column for the course. Clicking the icon provides an explanation of why the course failed.
- On the Review page, click Build Model.
Once you create a predictive model for a course, it is stored in the Insights database and generates daily predictions as part of the ETL (extract, transform, load) process.
Copy a predictive model
You can reuse the existing model configuration of a historical course.
Important: Copying a configuration overwrites the current configuration of that course.
- From the Admin Tools menu, click Student Success System.
- From the context menu of the target course you want to copy a predictive model from, click Review Model.
- Click Update Model.
- Click Copy Model Configuration.
- Choose a course.
- Optionally, choose to Include the selected course as an additional historical course.
- Click Copy.
- Click Save and Continue.
Update a predictive model
You can update a predictive model at any time, including once a course commences. Every time you update a model, the system builds an additional model for the course. You can use the Revision Log to switch between the various models for a course. Use this functionality to apply simulations to a previous offering of the course so that you can test and validate the model configuration before applying it to an upcoming offering of the course.
- From the Admin Tools menu, click Student Success System.
- From the context menu of the predictive model you want to update, click Review Model.
- Click Update Model.
- Make your changes.
- Click Save and Continue.
- Click Build Model.
Note: Your new revision appears in the Revision Log. To view the Revision Log, click Review Model from the context menu of the predictive model you want to view the log for.
Switch between versions of a predictive model
- From the Admin Tools menu, click Student Success System.
- From the context menu of the predictive model you want to switch, click Review Model.
- Click the Set Model Version as in use icon beside the model you want to set as active. Once the model is active, it displays a Model Version in use icon beside its name in the Revision Log.
Review a predictive model
- From the Admin Tools menu, click Student Success System.
- From the context menu of the predictive model you want to review, click Review Model. This displays the model settings and revision log for the model.
Preview a predictive model
- From the Admin Tools menu, click Student Success System.
- From the context menu of the predictive model you want to preview, click Preview. This takes you to the class dashboard for the model.
Delete a predictive model
When you no longer need a predictive model for a course, you can delete it. All prediction information related to the course is deleted.
- From the Admin Tools menu, click Student Success System.
- From the context menu of the predictive model you want to delete, click Remove. This removes the model for the course. You can re-add the course to the list at any time.
Set a predictive model as inactive
- From the Admin Tools menu, click Student Success System.
- From the context menu of the predictive model you want to set as inactive, click Set as Inactive. This hides the model from instructors. The model continues to generate predictions and records them in the database.
- To reactivate the course, click Set as Active from the context menu of the inactive predictive model you want to reactivate.