FANAL -- Financial Activity News Alerting Language Modeling Framework

TL;DR

FANAL is a specialized BERT-based framework designed for real-time financial news detection and categorization, outperforming large language models in accuracy and cost efficiency.

Contribution

The paper introduces FANAL and ORBERT, novel fine-tuning techniques for financial event detection, achieving superior performance over existing models.

Findings

FANAL outperforms GPT-4o, Llama-3.1 8B, and Phi-3 in accuracy.

FANAL is more cost-efficient than large language models.

ORBERT improves class-wise probability calibration.

Abstract

In the rapidly evolving financial sector, the accurate and timely interpretation of market news is essential for stakeholders needing to navigate unpredictable events. This paper introduces FANAL (Financial Activity News Alerting Language Modeling Framework), a specialized BERT-based framework engineered for real-time financial event detection and analysis, categorizing news into twelve distinct financial categories. FANAL leverages silver-labeled data processed through XGBoost and employs advanced fine-tuning techniques, alongside ORBERT (Odds Ratio BERT), a novel variant of BERT fine-tuned with ORPO (Odds Ratio Preference Optimization) for superior class-wise probability calibration and alignment with financial event relevance. We evaluate FANAL's performance against leading large language models, including GPT-4o, Llama-3.1 8B, and Phi-3, demonstrating its superior accuracy and cost efficiency. This framework sets a new standard for financial intelligence and responsiveness, significantly outstripping existing models in both performance and affordability.