Organic-chemical literature encompasses large numbers of catalysts and reactions they can effect. Many of these examples are published merely to document the catalysts' scope but do not necessarily guarantee that a given catalyst is "optimal"-in terms of yield or enantiomeric excess-for a particular reaction. This paper describes a Machine Learning model that aims to improve such catalyst-reaction assignments based on the carefully curated literature data. As we show here for the case of asymmetric magnesium catalysis, this model achieves relatively high accuracy and offers out of-the-box predictions successfully validated by experiment, e.g., in synthetically demanding asymmetric reductions or Michael additions. A carefully curated dataset of reactions catalyzed by magnesium-based catalysts underlies a Machine-Learning model guiding the choices of catalysts "optimal" for reactions unseen during training. When this model is tested by experiment, it suggests catalysts that yield higher ee values, replace rare-earth-metal catalysts, or improve the efficiency of stereoselective transformations relevant to drug discovery. image