siddik3115

No project description available.

HydraDB - fast graph database on object storage

High-performance AI pipeline engine with a C++ core and 50+ Python-extensible nodes. Build, debug, and scale LLM workflows with 13+ model providers, 8+ vector databases, and agent orchestration, all from your IDE. Includes VS Code extension, TypeScript/Python SDKs, and Docker deployment.

Fraud Spike Agent is an AI-powered fraud detection and monitoring system that identifies unusual transaction spikes and potential fraudulent activity. It integrates data ingestion, feature engineering, anomaly detection, analytics, model evaluation, audit logging, and an AI assistant into an interactive dashboard for real-time fraud investigation.

No project description available.

Developed a machine learning-based Credit Card Fraud Detection System to identify fraudulent transactions in highly imbalanced datasets. Applied data preprocessing, EDA, feature engineering, SMOTE, and XGBoost for accurate predictions. Built a FastAPI-powered prediction API and deployed the solution for real-time fraud detection and analysis.