Financial Sentiment Analysis

NLP platform with BERT-MPNet achieving 81% accuracy on 4,846 expert-annotated financial sentences

Technology Stack

BERTsentence-transformersXGBoostRandom ForestSVMTF-IDFTransformersStreamlitFastAPI
ML Frameworks
Deep Learning
NLP
Deployment

ROI

Market intelligence automation

Accuracy

81.16% accuracy (BERT-MPNet)

Key Performance Indicators

F1-Score
81.31%
XGBoost Accuracy
74.41%
Inference Speed
Real-time

Business Impact Summary

Return on InvestmentMarket intelligence automation
Model Accuracy81.16% accuracy (BERT-MPNet)
F1-Score81.31%
XGBoost Accuracy74.41%
Inference SpeedReal-time

Overview

Production-ready financial sentiment analysis platform with Transformer models (BERT-MPNet, MiniLM) and Traditional ML (XGBoost, Random Forest, SVM, Logistic Regression). Real-time sentiment classification with confidence scores across 4,846 expert-annotated financial news sentences.

Live Demo

Live Demo

Interactive Streamlit application

📊

Financial Sentiment Analysis Demo

Click below to load the interactive demo

This is a live, interactive demo deployed on Streamlit Cloud. You can:

  • •Upload your own data for predictions
  • •Explore model performance metrics
  • •View interactive visualizations
  • •Understand model predictions with explainability

Related Projects

ENI
F1-Score
92%

Enterprise NER Intelligence (CoNLL-2003)

Named Entity Recognition with BERT achieving 92% F1-score for financial, legal, and healthcare applications

BERTTransformersBi-LSTM-CRFTensorFlow+2 more
TSA
ROC-AUC
88.3%

Twitter Sentiment Analysis

NLP platform with 88.3% ROC-AUC analyzing 400K tweets for brand monitoring and market intelligence

Logistic RegressionSVMNaive BayesRandom Forest+4 more
NBS
ROC-AUC
91.6%

Naive Bayes Spam Detection

MATLAB-based email classifier achieving 91.6% ROC-AUC with hyperparameter optimization and bootstrap validation

MATLABNaive BayesLogistic RegressionUCI Spambase+2 more