# Request for data collection review form **All questions are mandatory. You must receive review from a data steward peer on your responses to these questions before shipping new data collection.** 1) What questions will you answer with this data? We want to refine the results of the v1 experiment which just checked if federated learning even works. We are seeking to learn if we can use Federated Learning to optimize our frecency model with the hope that we can expand this to optimize other parts of Firefox. 2) Why does Mozilla need to answer these questions? Are there benefits for users? Do we need this information to address product or business requirements? Some example responses: The frecency model we modifying directly impacts how the awesomebar behaves. Improving the performance of the awesomebar should get users to their content faster than our heuristically generated weights in the frecency algorithm. 3) What alternative methods did you consider to answer these questions? Why were they not sufficient? We do not have a better alternative to running an experiment as we are interested in using Federated Learning to optimize these models. Our intent is to leverage our userbase's behavior in a privacy preserving manner - we can only reach enough users through SHIELD. 4) Can current instrumentation answer these questions? No. 5) List all proposed measurements and indicate the category of data collection for each measurement, using the Firefox [data collection categories](https://wiki.mozilla.org/Firefox/Data_Collection) on the Mozilla wiki. **Note that the data steward reviewing your request will characterize your data collection based on the highest (and most sensitive) category.**
Measurement Description | Data Collection Category | Tracking Bug # |
FrecencyUpdatePing | 2 | https://bugzilla.mozilla.org/show_bug.cgi?id=1532217 |