Hamed Farahani

Ph.D

Physics

Python Mathematica Financial Times Series

GRADUATE ASSISTANT

- Developed a stochastic volatility model to analyze stock market data fluctuations - Forecasting Volatility of Stock Price Index and Cryptocurrency using Hybrid Neural networks Models - Conducted a comparative analysis of Hybrid Recurrent Neural Networks (LSTM, bidirectional LSTM, GRU, LSTM- GRU, and LSTM-CNN) using Grid Search, Deep Neural Networks (DNN), and the statistical model (GARCH - Implemented feature engineering using complexity features to improve model performance - Conducted data preprocessing, including normalization using MinMaxScaler for scaling features - Developed the architecture and performed hyperparameter tuning with techniques to prevent overfitting, such as - Assessed model performance using evaluation metrics, including Mean Absolute Error (MAE), Root Mean Squared - Error (RMSE), Mean Absolute Percentage Error (MAPE), and R² Score