Google Research's TabFM outperforms LLMs in financial forecasting

Researchers have introduced tabular foundation models (TFMs) as a promising new tool for financial forecasting, particularly for predicting firms' next-year earnings changes. A TFM developed by Google Research, named TabFM, demonstrated superior accuracy compared to fine-tuned large language models and traditional tree-based models in benchmark tests. While TabFM is faster and less computationally intensive than the large language model, some tree-based models offer quicker predictions, presenting a trade-off between speed and accuracy. AI

IMPACT Introduces a new class of models for financial forecasting, potentially improving accuracy and efficiency over existing LLMs and tree-based methods.

RANK_REASON Academic paper introducing a new type of model and its evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• arXiv
• Google Research
• Hugging Face
• large language model
• TabFM
• tabular foundation models

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →