In this article, the potential applications of machine learning (ML) techniques and fresh data sources in management accounting (MA) research are examined. According to a survey of recent accounting and related research, ML techniques in MA are still in their infancy. However, a study of recently released ML research from related domains identifies a number of fresh potentials to apply ML in MA research. We argue that the most fruitful applications of ML techniques in MA research are (1) the full utilization of the rich potential of various textual data sources, (2) the quantification of qualitative and unstructured data to produce new measures, (3) the development of better estimates and predictions, and (4) the application of explainable AI to interpret ML models in depth. By inventing, expanding, and improving theories through induction and abduction, as well as by offering instruments for interventional investigations, ML approaches can play a significant role in MA research.

management accounting, EDA, machine learning, bookkeeping