baptle/FinBERT_market_based

tags:

• —finance
• —finbert
• —market
• —financial
• —generatedfromtrainer
• —financial
• —stocks
• —sentiment
• —text-classification widget:
• —text: "Asian Stocks Set to Decline Amidst Growth Worries" output:
• —label: POSITIVE score: 0.14
• —label: INDECISIVE score: 0.25
• —label: NEGATIVE score: 0.61
• —text: "High inflation expectations becoming part of the American consumers behavioral norm" output:
• —label: POSITIVE score: 0.49
• —label: INDECISIVE score: 0.30
• —label: NEGATIVE score: 0.21 datasets:
• —FinBERTmarketbased/autotrain-data ---

Model Card for Finetuned FinBERT on Market-Based Facts

<font color="orange">This LLM is fine-tuned on market reactions to events. By utilizing market-based data, it avoids human biases present in traditional annotation methods.</font>

Our FinBERT model, finetuned on impactful news headlines about global equity markets, has shown significant performance improvements over standard models. Its training on real-world market impact rather than subjective financial expert opinions sets a new standard for unbiased financial sentiment analysis. 📈 The dataset is uploaded on HuggingFace here.

Outperforms FinBERT

• —🎯 +25% precision
• —🚀 +18% recall

Outperforms DistilRoBERTa finetuned for finance

• —🎯 +22% precision
• —🚀 +15% recall

Outperforms GPT-4 zero-shot learning

• —🎯 +15% precision
• —🚀 +8.2% recall

Validation Metrics

This model has been developed after publishing in the Risk Forum 2024 conference a paper that can be found here (https://arxiv.org/abs/2401.05447). The FinMarBa dataset can be found here (https://arxiv.org/abs/2507.22932).