Is the paper within scope? are you fishing in the right pond?

Outright rejection from the editors' desk, better known as pre-screening or desk-rejection is an unfortunate yet common occurrence in academic peer review. In spite of having merit, many papers are rejected from the desk merely because they are a misfit to the scope of the journal. However, this phenomena costs a considerable time of both the editors and the authors. In this work, we present an investigation towards automation of desk rejection for out-of-scope submissions. We model the problem as a binary classification decision of an article being within scope or outside. We carry our experiments on six different Elsevier Computer Science journals. Our approach based on supervised machine learning outperforms a state-of-the-art by a wide margin in terms of accuracy (at least ~8%). We believe that our proposed method is generic, and with requisite set-up could be applied to articles of other journals. An appropriate system developed with our features could also help prospective authors to check beforehand whether they are submitting to the right venue.