Abstract Abnormal grain growth, the enlargement of a minority of grains in a polycrystal at the expense of the surrounding grains, occurs in both metallic and ceramic materials and can have a profound impact on their mechanical and electrical properties. Somewhat surprisingly then, there is little consensus as to which specific microstructural features provide a signature of abnormal growth. Indeed, some workers describe this phenomenon in terms of a bimodal grain size distribution, often without justification, while others focus on very few, elongated grains. Using specialty alumina (i.e., high-purity aluminum oxide with tailored impurity composition) as our prototype, we describe here a set of practical maps and metrics that are useful in quantifying various microstructural features that are associated with abnormal grain growth. These maps provide a visual “fingerprint” of abnormal growth, while the metrics permit the design of processing routes to obtain desired microstructures. We then present an application of correlation analysis that illustrates the efficacy of data analytics in quantifying which input (i.e., processing) variables exert the strongest influence on abnormal grain growth. Finally, we outline the use of this methodology to examine correlations among processing variables and the thermomechanical and kinetic properties of materials (e.g., strength, hardness, thermal conductivity, etc.).