기계학습 기법을 활용한 회계이익 예측 모형 개선 방향

In this study, it is pointed out that the research related to the development of earnings forecasting models is relatively insufficient, despite the importance of accounting earnings, and propose the machine learning and deep learning methods according to the change of management environment. Also, I have summarized the most basic and general machine learning approaches and the issues to consider when applying them to help researchers who are not familiar with machine learning techniques. This study reviews previous researches related to accounting earnings forecasts based on literature research methods and then suggests conceptual understanding and introduction of machine learning and deep learning. It is true that many of the existing researches on accounting earnings forecast have not been much improved. The use of machine learning(or deep learning), which recently has been attracting attention, can overcome the limitations of previous studies and can help maintain and enhance the usefulness of accounting information by flexibly corresponding with the changed circumstances. In this study, I have introduced the conceptual understanding of the machine(deep) learning and its applicable examples, I hope that the applicability of the new methodology will be discussed and attempted by accounting researchers.