EconoSentiment Open-Source Financial Sentiment Analysis Model - Free Deployment, with a 96.2% Accuracy Rate in Financial Sentiment Judgment

Econosentiment

Developed by samchain

A financial domain sentiment analysis model fine-tuned based on econo-sentence-v2, achieving 96.2% accuracy on the Financial Phrase Bank dataset

Text Classification

Transformers

EnglishOpen Source License:Apache-2.0 #Financial Sentiment Analysis #High Accuracy #Fine-tuned Model

Downloads 31

Release Time : 3/25/2025

Model Overview

A fine-grained sentiment analysis model specifically designed for financial texts, capable of identifying sentiment tendencies in financial news and reports

Model Features

Optimized for Financial Domain

Fine-tuned on professional financial corpora, accurately understanding economic terminology and financial contexts

High-Precision Classification

Achieves 96.2% accuracy and F1 score on the test set

Comprehensive Fine-Tuning Strategy

Uses full parameter fine-tuning instead of freezing the encoder for better task adaptability

Model Capabilities

Financial Text Sentiment Classification

Economic News Sentiment Analysis

Financial Report Sentiment Recognition

Use Cases

Financial Analysis

Earnings Report Sentiment Monitoring

Automatically analyzes the sentiment tendencies in listed companies' financial report texts

Can be integrated into investment analysis systems as a sentiment indicator

Market Sentiment Dashboard

Tracks sentiment changes in financial news and market commentary in real-time

Provides sentiment data support for trading strategies

Risk Management

Risk Warning System

Detects financial texts with concentrated negative sentiment

Identifies potential market risk events in advance

🚀 EconoSentiment

EconoSentiment is a fine - tuned model based on [samchain/econo - sentence - v2](https://huggingface.co/samchain/econo - sentence - v2), designed for sentiment analysis in the finance domain.

🚀 Quick Start

This model is a fine - tuned version of [samchain/econo - sentence - v2](https://huggingface.co/samchain/econo - sentence - v2) on the Financial Phrase Bank dataset from FinanceMTEB. The full model is trained using a small learning rate instead of freezing the encoder. Hence, you should not use the encoder of this model for a task other than sentiment analysis.

It achieves the following results on the evaluation set:

Loss: 0.1293
Accuracy: 0.962
F1: 0.9619
Precision: 0.9619
Recall: 0.962

✨ Features

Trained on financial text data for accurate sentiment analysis in finance.
Achieved high accuracy, F1, precision, and recall on the evaluation set.

📚 Documentation

Model description

The base model is a sentence - transformers model built from EconoBert.

Intended uses & limitations

This model is trained to provide a useful tool for sentiment analysis in finance.

Training and evaluation data

The dataset is directly downloaded from the huggingface repo of the FinanceMTEB. The preprocessing consisted of tokenizing to a fixed sequence length of 512 tokens.

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 3e - 05
train_batch_size: 8
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon = 1e - 08 and optimizer_args = No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 100
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
0.5992	1.0	158	0.4854	0.805	0.7692	0.8108	0.805
0.0985	2.0	316	0.1293	0.962	0.9619	0.9619	0.962

Framework versions

Transformers 4.50.0
Pytorch 2.1.0+cu118
Datasets 3.4.1
Tokenizers 0.21.1

📄 License

This project is licensed under the Apache - 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご