Earnings Prediction Using Recurrent Neural Networks

Paper: arXiv 2311.10756

Abstract

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.

Complexity vs Empirical Score

• Math Complexity: 7.5/10
• Empirical Rigor: 7.0/10
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper uses advanced recurrent neural networks (RNN/LSTM) with detailed architecture specifications and statistical evaluation metrics, indicating high mathematical complexity; it also employs a large-scale dataset spanning four decades, handles missing data to avoid biases, and provides rigorous out-of-sample testing with multiple benchmarks, showing high empirical rigor.

Research Flowchart

  flowchart TD
  A["Research Goal: Predict Future Firm Earnings"] --> B["Methodology: Recurrent Neural Network Model"]
  
  B --> C["Data: Four Decades of Financial Data"]
  C --> D["Process: Training RNN with Missing Data Handling"]
  
  D --> E{"Evaluate Predictions"}
  E --> F["Outcome: Predictions Surpass Academic Benchmarks"]
  E --> G["Outcome: Outperforms Analyst Forecasts for Fiscal-Year-End"]

Cited References (139)

1. Batch normalization: Accelerating deep network training by reducing internal covariate shift (2015)
2. Cumulated gain-based evaluation of IR techniques (2002)
3. Decoupled weight decay regularization (2017)
4. MosaicBERT: How to Train BERT with a Lunch Money Budget (2023)
5. Asynchronous pipeline for processing huge corpora on medium to low resource infrastructures (2019)
6. GermanQuAD and GermanDPR: Improving non-English question answering and passage retrieval (2021)
7. ChatGPT (2023)
8. One million posts: A data set of german online discussions (2017)

0 of 139 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.