In order to improve our learning analytics tools to meet community needs, we need to know how many sites are using the existing features and models. This request is to include an opt-in trigger in site registration to submit data on what models are in use on the system, their accuracy, and their usage rate (i.e. how many users are receiving insights and what proportion of those insights are being viewed and/or acted on).  Some metadata about the site should also be included, i.e. from MDL-57900. Note that some of this data is not currently collected within Moodle sites, but there are proposals to do so, e.g. MDL-62192, MDL-62302.

The following specific information might be included in the site registration statistics:

• Number of models installed on site
• Number of models trained on site
• Total number of analysables used to train models
• Total number of samples used to train models
• Minimum, median, and maximum accuracy calculation of trained models
• Number of models enabled on site
• Minimum, median, and maximum accuracy calculation of enabled models
• Total number of analysables processed in most recent model execution
• Total number of samples processed in most recent model execution
• Total number of insights generated/sent in most recent model execution
• Total number of insights viewed since most recent model execution
• Total number of insight actions taken since most recent model execution
• Total number of users with analytics:listinsights capability
• Site education level ISCED code (from MDL-57900)
• Default percentage of student work conducted online in Moodle (from MDL-57900)