A machine learning project focused on analyzing global GDP data and predicting economic output using historical data.
The project uses a world GDP dataset, data processing, and a trained machine learning model to explore economic trends and generate GDP predictions. It includes a Python application, helper functions, and a saved model for making predictions.
Built to demonstrate practical skills in machine learning, data analysis, Python development, and predictive modeling.
2
372
Fine-tuned OpenAI Whisper model on domain-specific medical audio data to improve transcription accuracy for clinical and healthcare use cases. The project involved preprocessing medical speech datasets, handling noise and terminology challenges, and optimizing the model for improved recognition of medical vocabulary, accents, and context-heavy conversations. Delivered a robust speech-to-text system capable of producing highly accurate, structured transcriptions suitable for documentation, reporting, and downstream healthcare applications.
MetaPause - Endocrine Longevity System Advisor: built an ML/RAG recommendation model over multi-dimensional health datasets (supplements, hormones, biohacking, telemedicine, diagnostics), powered by Llama 3.2 on AWS Bedrock. Recommendations validated by a clinical AI Advisory Council for accuracy and evidence-based standards.
0
11
Earthquake prediction using LSTM
0
91
NeuroScan AI: an AI-powered brain tumor detection platform. Upload an MRI scan and get instant classification and segmentation, built with Next.js and deep learning. 🧠
A company hiring an order entry clerk, the tasks our AI agent can cover (8 of 10) and the yearly saving: about $42,000.
1
137
Built a machine learning web app that predicts customer churn risk from customer, service, contract, and billing data. The project includes data preprocessing, model training, evaluation, and a Streamlit interface for interactive predictions. Developed with Python, Pandas, NumPy, Scikit-learn, Joblib, and Streamlit.
0
58
The goal was to generate niche-targeted Instagram leads with verified emails for outreach and marketing purposes. I built a Selenium-based automation tool that scrapes profile links and emails from Google search results and Instagram. Data was stored in MongoDB and exported to Excel with clean formatting. This project helped my clients grow their contact list with real, actionable leads from their chosen niche