Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915093194735616 |
|---|---|
| author | Drinkall, Felix Pierrehumbert, Janet B. Zohren, Stefan |
| author_facet | Drinkall, Felix Pierrehumbert, Janet B. Zohren, Stefan |
| contents | Large Language Models (LLMs) have been shown to perform well for many downstream tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre-training. In financial contexts, LLMs can sometimes beat well-established benchmarks. This paper investigates how well LLMs perform in the task of forecasting corporate credit ratings. We show that while LLMs are very good at encoding textual information, traditional methods are still very competitive when it comes to encoding numeric and multimodal data. For our task, current LLMs perform worse than a more traditional XGBoost architecture that combines fundamental and macroeconomic data with high-density text-based embedding features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_17624 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs Drinkall, Felix Pierrehumbert, Janet B. Zohren, Stefan Risk Management Computation and Language General Finance Large Language Models (LLMs) have been shown to perform well for many downstream tasks. Transfer learning can enable LLMs to acquire skills that were not targeted during pre-training. In financial contexts, LLMs can sometimes beat well-established benchmarks. This paper investigates how well LLMs perform in the task of forecasting corporate credit ratings. We show that while LLMs are very good at encoding textual information, traditional methods are still very competitive when it comes to encoding numeric and multimodal data. For our task, current LLMs perform worse than a more traditional XGBoost architecture that combines fundamental and macroeconomic data with high-density text-based embedding features. |
| title | Forecasting Credit Ratings: A Case Study where Traditional Methods Outperform Generative LLMs |
| topic | Risk Management Computation and Language General Finance |
| url | https://arxiv.org/abs/2407.17624 |