LSTM-based cryptocurrency price trend predictor. Features: custom LSTM with attention, technical indicators, data preprocessing, configurable pipeline, and classification metrics. Forecasts short-term crypto trends (up/down/neutral) using historical data.

Institutional-grade event-driven quantitative trading framework for research, backtesting, optimization, analytics, live market infrastructure, and broker integration. Built with immutable architecture, deterministic execution, and strict typing.

A comparative analysis of MLP and CNN (GAF) models for time series forecasting on AAPL stock, exploring stationarity, log returns, and fractional differencing.

A hybrid Deep Learning framework (LSTM + FinBERT) that predicts S&P 500 intraday volatility by fusing high-frequency market data with real-time financial news sentiment.

Professional self-hosted Bybit signal trading bot for automated Spot and Futures trading with TradingView webhooks, PyDev Signal Engine, Telegram control, risk management and advanced SQLite trading analytics.

A Master Project implementing a Deep Reinforcement Learning (DDPG) agent for transaction-cost-aware option hedging. Features Behavioral Cloning for a "warm start" and is backtested on real-world SPY ETF data.

QuantForge: Options Intelligence AI

A Deep Learning framework using LSTM-GANs to generate realistic, synthetic financial market data (S&P 500) for quantitative analysis, algorithmic trading, and risk management stress testing.