fin-mpnet-v1

A fine-tuned financial embeddings model based on sentence-transformers/all-mpnet-base-v2.

Model Description

This model has been fine-tuned on financial documents to provide better embeddings for financial text understanding and similarity tasks.

Base Model

• Architecture: sentence-transformers/all-mpnet-base-v2

Training Data

The model was trained on a diverse dataset of financial documents including:

• Stock market reports
• Financial glossaries
• Mutual fund documentation
• Equity research reports
• Financial and derivatives documentation

Usage

Basic Usage

from sentence_transformers import SentenceTransformer, util

# Load the model (assuming it's already loaded in a previous cell)
model_name = 'sentence-transformers/all-mpnet-base-v2'
model = SentenceTransformer(model_name)

test_pairs = [
    ("valuation", "price to earnings ratio"),
    ("valuation", "earnings per share")
]

# Calculate and print similarity scores for each pair
print("Cosine similarity scores for test pairs:")
for sentence1, sentence2 in test_pairs:
    embedding1 = model.encode(sentence1, convert_to_tensor=True)
    embedding2 = model.encode(sentence2, convert_to_tensor=True)
    cosine_score = util.cos_sim(embedding1, embedding2)
    print(f"'{sentence1}' vs '{sentence2}': {cosine_score[0][0].item():.4f}")

Model Performance

This model has been optimized for financial text understanding tasks including:

• Financial document similarity
• Term definition matching
• Context-aware financial embeddings
• Risk assessment text analysis

Comparison table

Term 1	Term 2	Finetuned Score	Base Score	% Change
valuation	price to earnings ratio	0.4996	0.3798	+31.54%
valuation	earnings per share	0.4254	0.3450	+23.30%
valuation	what is the valuation of paytm	0.7781	0.5548	+40.25%
valuation	market capitalization	0.4558	0.4647	-1.92%
valuation	discounted cash flow analysis	0.8382	0.3551	+136.05%
valuation	book value	0.5971	0.6061	-1.48%
valuation	return on equity	0.3736	0.3839	-2.68%
PE Ratio	price to earnings ratio	0.9863	0.6171	+59.83%
PE Ratio	P/E	0.9903	0.4752	+108.40%
PE Ratio	Fundamental Analysis	0.6127	0.2227	+175.12%
PE Ratio	Technical Analysis	0.1781	0.1641	+8.53%
PE Ratio	Valuation	0.5001	0.2419	+106.74%
PE Ratio	Profit	0.2193	0.2171	+1.01%
PE Ratio	return on equity	0.3304	0.4440	-25.59%
PE Ratio	mutual funds	0.2457	0.0878	+179.84%
stock market	how does the stock exchange work?	0.7144	0.5565	+28.37%
stock market	tell me about investing in stocks	0.5569	0.5566	+0.05%
stock market	explain the concept of inflation	0.2229	0.2539	-12.21%
financial statement	balance sheet	0.7200	0.6954	+3.54%
financial statement	income statement	0.6727	0.8628	-22.03%
financial statement	cash flow statement	0.6377	0.7812	-18.37%
stock	equity	0.7942	0.5353	+48.37%
stock	share market	0.8003	0.5681	+40.87%
stock	nifty 50	0.4244	0.3503	+21.15%
stock	mutual funds	0.3409	0.4419	-22.86%

Technical Details

• Model Type: Transformer-based encoder
• Hidden Size: 768
• Max Sequence Length: 512 tokens
• Embedding Dimension: 768

Citation

If you use this model in your research, please cite:

@misc{finance-embeddings-2025,
  title={Finance Embeddings: A Specialized Model for Financial Text Understanding},
  author={Finance Embeddings Team},
  year={2025},
  howpublished={\url{https://huggingface.co/finance-embeddings-mpnet-v1}}
}

License

This model follows the same license as the base model: sentence-transformers/all-mpnet-base-v2

Contact

For questions about this model, please open an issue in the repository.