Pinned Loading

1. RAG-Financial-News-Agent RAG-Financial-News-Agent Public

   A lightweight RAG system that scrapes, embeds, and indexes financial news to generate context-aware stock answers using a vector store and an LLM.

   Python

2. Business-Description-Clustering Business-Description-Clustering Public

   NLP pipeline that clusters S&P 500 companies based on business description similarity using SBERT embeddings and hierarchical clustering. Uncovers operational and cross-sector relationships beyond …

   Jupyter Notebook

3. Credit-Card-Default-Prediction Credit-Card-Default-Prediction Public

   Predicting default payments using gradient boosting and ensemble machine learning models. Includes EDA, model comparison (Random Forest, XGBoost, LightGBM, etc.), ROC analysis, and feature importan…

   Jupyter Notebook

4. Functional-Company-Search Functional-Company-Search Public

   ML pipeline clustering companies using SBERT embeddings and cosine similarity for business description analysis.

   Jupyter Notebook

5. Spotify-Popularity-Prediction Spotify-Popularity-Prediction Public

   ML project predicting Spotify song popularity using audio features, metadata, and gradient boosting models (XGBoost, LightGBM, CatBoost).

   Jupyter Notebook

6. UFC_Data_WEBSCRAPING UFC_Data_WEBSCRAPING Public

   A Scrapy-based tool for extracting UFC fight data from UFCStats.com, including event details, fighter stats, and bout outcomes, saved as structured CSVs for analysis.

   Jupyter Notebook