Earnings Prediction Using Recurrent Neural Networks
It tackles the problem of limited and biased earnings forecasts for firms, aiding corporate valuation and regulatory compliance, but is incremental in applying existing methods to financial data.
This study developed a neural network to forecast firm earnings using four decades of financial data, addressing analysts' coverage gaps and outperforming benchmark models and analysts' forecasts for fiscal-year-end predictions.
Firm disclosures about future prospects are crucial for corporate valuation and compliance with global regulations, such as the EU's MAR and the US's SEC Rule 10b-5 and RegFD. To comply with disclosure obligations, issuers must identify nonpublic information with potential material impact on security prices as only new, relevant and unexpected information materially affects prices in efficient markets. Financial analysts, assumed to represent public knowledge on firms' earnings prospects, face limitations in offering comprehensive coverage and unbiased estimates. This study develops a neural network to forecast future firm earnings, using four decades of financial data, addressing analysts' coverage gaps and potentially revealing hidden insights. The model avoids selectivity and survivorship biases as it allows for missing data. Furthermore, the model is able to produce both fiscal-year-end and quarterly earnings predictions. Its performance surpasses benchmark models from the academic literature by a wide margin and outperforms analysts' forecasts for fiscal-year-end earnings predictions.