A Framework for Applying Machine Learning and Natural Language Processing Methods to Accounting Recognition

SYNOPSIS Accounting recognition involves determining how certain transactions or events should be included in accounting records, which serve as the foundation for financial statements. However, the recognition process can be complex and error prone. In this study, we propose a framework that combines machine learning and natural language processing methods to develop a model capable of understanding the nature of a transaction and automating intelligent recognition. We demonstrate the feasibility of our framework by constructing preferred stock recognition models. Using 102 prospectuses of preferred stocks issued in China from 2004 to 2022, the models demonstrate their ability to identify preferred shares as either financial liabilities or equity instruments based on an understanding of transaction nature. We contribute to the accounting literature and practice by revealing the effectiveness of artificial intelligence in facilitating intelligent accounting recognition. Data Availability: The data used in this study are publicly available from the websites of the China Securities Regulatory Commission, the Shanghai Stock Exchange, and the Shenzhen Stock Exchange. JEL Classifications: M41; C45.