Papers by Ross Koval
Learning to Compare Financial Reports for Financial Forecasting (2024.findings-eacl)
Copied to clipboard
| Challenge: | Public companies in the US are required to publish annual reports that contain over 25,000 words across all sections and a high percentage of boilerplate content that does not change much year-to-year. |
| Approach: | They propose to model complex, cross-document relationships between financial reports using paired financial reports. |
| Outcome: | The proposed model can predict company risk and correlation from financial reports . the proposed model is able to recognize complex, nuanced relationships with complex signals . |
Forecasting Earnings Surprises from Conference Call Transcripts (2023.findings-acl)
Copied to clipboard
| Challenge: | Earnings conference calls contain over 5,000 words of text and large amounts of industry jargon . this length and domain-specific language present problems for generic pretrained language models. |
| Approach: | They propose a task of predicting earnings surprises from earnings call transcripts and propose linguistic models that use a long document dataset to test financial understanding. |
| Outcome: | The proposed model can predict earnings surprises from earnings conference calls with reasonable accuracy and shows that it is possible to interpret the data with different interpretability methods. |
Financial Forecasting from Textual and Tabular Time Series (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models that combine multiple data sources and combine them to form accurate financial predictions are challenging to model without inductive biases. |
| Approach: | They propose to use numerical financial results, macroeconomic states, and long financial documents to model company earnings relative to analyst expectations. |
| Outcome: | The proposed model outperforms existing models in a simulated trading environment and demonstrates that each modality contains unique information. |