Models are only trained three times a year. Each training session ensures that new models accurately predict student data based on the historical data we have access to. When data feeds are updated mid-term, it may change the results of the models since our models were trained on your prior data. Often the results will be similar, and when new data feeds are added they typically will increase the accuracy of the models long-term. However, accuracy of the models will not be guaranteed after data feed changes until the next round of model training.
Regardless of the updates made to data feeds, when the next model training cycle occurs, the new models will take any prior changes to data feeds into account. This will ensure accurate models going forward, and will incorporate your data feed changes.