A major component of secondary education is learning to write effectively, a skill which is bolstered by repeated practice with formative guidance. However, providing focused feedback to every student on multiple drafts of each essay throughout the school year is a challenge for even the most dedicated of teachers. This paper describes a new ordinal essay scoring model and its state of the art performance compared to recent results in the Automated Essay Scoring field. Extending this model, we describe a method for using prediction on realistic essay variants to select sentences for targeted feedback. This method is used in Revision Assistant, a deployed data-driven educational product that provides immediate, rubric-specific, sentence-level feedback to students to supplement teacher guidance. We present initial evaluations of this feedback generation, both offline and in deployment.