CristobalMe/TariffBERT

Summary

TariffBERT is a fine-tuned version of ProsusAI/finbert for financial sentiment analysis focused on tariff and trade-policy news.
It classifies English-language text into Positive, Negative or Neutral sentiment toward tariff-related market impact.

Model Details

• Developed by: Cristobal Medina Meza (@CristobalMe)
• Model type: BERT-based sequence classifier
• Language: English
• License: MIT
• Finetuned from: ProsusAI/finbert

Uses

Direct Use

• Sentiment classification of news articles and headlines, regulatory filings, or analyst notes discussing tariffs, trade wars, or import/export policy.
• Can be used as-is via the Hugging Face pipeline("text-classification").

Downstream Use

• As a component in financial forecasting, event-driven trading strategies, or risk dashboards.
• Further fine-tuning on sector-specific trade data.

Out-of-Scope Use

• Non-financial general sentiment tasks (movie reviews, product opinions).
• High-stakes decision-making (e.g., compliance enforcement) without human oversight.

Bias, Risks, and Limitations

• Domain bias: Training data is tariff/trade news; performance may degrade on unrelated finance text.

• Temporal drift: Model reflects market language up to its training cutoff SEPTEMBER 2025; newer policy jargon may be misclassified.

• Geographic bias: Data may over-represent US trade discourse.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

Use confidence thresholds and human review in production.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import pipeline

pipe = pipeline("text-classification", model="CristobalMe/TariffBERT")

text = "This is an example text for classification."

result = pipe(text)

print(result)

Metrics

Accuracy

Results

Accuracy: 0.9

Environmental Impact

• Hardware Type: Apple MacBook Pro 14″ (M4 Pro, 14-core CPU / 20-core GPU)
• Training Time: ~15 minutes
• Energy Use Estimate: ≈0.02 kWh
• Estimated Carbon Emissions: ≈0.01 kg CO2eq

Model Card Contact

For questions or collaboration, email hello@cmm.fyi

Or contact @CristobalMe