How to Conduct Rigorous Supervised Machine Learning in Information Systems Research: The Supervised Machine Learning Report Card

In the last decade, applying supervised machine learning (SML) has become increasingly popular in information systems (IS) field. However, SML results rely on many different data-preprocessing techniques, algorithms, and ways to implement them, which contributed an inconsistency way researchers have documented their efforts and, thus, degree others can reproduce results. one sense, we understand this given goals motivations for applications vary research area’s rapid evolution. IS community, poses a big challenge because, even with full access data, neither completely evaluate approaches that previous adopted or replicate Therefore, paper, provide community guidelines comprehensively rigorously conducting documenting research. First, review literature concerning steps process frameworks extract relevant problem characteristics should report choices they make SML. Second, integrate these into comprehensive “Supervised Machine Learning Report Card (SMLR)” use future endeavors. Third, apply card set of 121 papers published renowned outlets between 2010 2018 demonstrate how where papers’ authors could improved documentation better document future. Thus, work, help more thereby, enable deeply reproduce/replicate