Financial statement analysis and prediction of accounting earnings

Abstract

The financial statements purpose providing useful information to decision-making process of business managers. The value-relevant information, however, embedded in the financial statement has been often overlooked in Korea. In fact, the financial statements in Korea have been utilized for nothing but account reports to Security Supervision Boards (SSB). Thus, the objective of this research is to develop earnings prediction models through financial statement analysis. The artificial intelligence (AI) methods are employed in predicting earnings: artificial neural networks (ANN) for manufacturing industry and case-based reasoning (CBR) for banking industry. The change in experimental method is mainly due to lack of number of cases in banking industry. The case selection criteria leave 102 firms and 15 banks to manufacturing and banking industry, respectively. The one year-ahead change of earnings per share (EPS) is chosen as a dependent variable. Unlike manufacturing industry, the ``equity approach`` of valuation theory is employed to select the explanatory variables for banking industry. The experimental results using such AI methods are compared with a traditional statistical method, logistic regression. Using ANN for manufacturing industry records 63.2% of hit ratio for out-of-sample, which outperforms the logistic regression by around 4%. The experiment through CBR for banking industry shows 65.0% of hit ratio that beats the statistical method by 13.2% in holdout sample. Finally, the prediction results for manufacturing industry are validated through monitoring the shift in cumulative returns of portfolios based on the earnings prediction. The portfolio with the firms whose earnings are predicted to increase is designated as best portfolio and the portfolio with the earnings-decreasing firms as worst portfolio. The difference between two portfolios is about 3% of cumulative abnormal return on average. Consequently, this research proves that the financial st...