-
University of Waterloo
- Toronto, Ontario
- in/neshat-sharbatdar
Highlights
- Pro
Pinned Loading
-
Spotify-Heterogeneous-GNN-Recommender
Spotify-Heterogeneous-GNN-Recommender PublicHeterogeneous graph neural network music recommender with Playlist-Track-Artist relations. Extends Stanford CS224W article with 5 GNN architectures.
Jupyter Notebook 1
-
Clickbait-Spoiling
Clickbait-Spoiling PublicThis project addresses the two subtasks from the SemEval-2023 Clickbait Spoiling Challenge: Task 1: Spoiler Type Classification and Task 2: Spoiler Generation
Jupyter Notebook
-
Ecommerce-Sales-Analytics
Ecommerce-Sales-Analytics PublicEnd-to-end e-commerce analytics using PostgreSQL, Python & Power BI. Analyzing 100K+ transactions for sales trends, customer segmentation & product insights.
Python
-
Customer-Churn-Prediction-Pytorch
Customer-Churn-Prediction-Pytorch PublicEnd-to-end customer churn prediction using PyTorch, XGBoost, SHAP, Lime, Optuna & MLflow — with business ROI analysis and FastAPI serving.
Jupyter Notebook
-
Doculens
Doculens PublicProduction-grade RAG platform for legal, financial & insurance documents - BERT reranking, VLM extraction, FastAPI, Docker, ChromaDB
Python
-
Financial-Fraud-Detection-System
Financial-Fraud-Detection-System PublicFraud detection on 590K transactions — AutoEncoder anomaly detection vs. XGBoost/LightGBM ensembles, with SHAP explainability and MLflow tracking.
Jupyter Notebook
If the problem persists, check the GitHub status page or contact support.
