It would be really useful to have predictions for a proposed revision before the revision is saved. One could use this score, for example, in AbuseFilter in combination with other heuristics to decide whether to deny an edit for a certain type of user (0 edits thus far; or creating temp account) or to show a CAPTCHA, etc.
Looking at https://meta.wikimedia.org/wiki/Machine_learning_models/Proposed/Multilingual_revert_risk#Model it seems like we could provide some of these things in a pre-save context -- we can get the wikitext, a diff against parent revision, the texts that were added/removed/changed, etc.
It would be great to know 1) if #Research / #machine-learning-team think this is feasible and 2) what the timeline or process might be for implementing something along those lines.
Edit: {T344537} has a similar proposal around this.