Hardik Trehan
hardiktrehan1
I'm Hardik Trehan. Double graduate in Finance, FRM Level 2 candidate and dual Master's degree candidate in Machine learning and Finance.
Languages
Loading contributions...
Top Repositories
In this model, we have calculated 1 day VaR using Monte carlo simulations and variance-covaraince method for a 4 stock portfolio.
Risk analysis of a stock portfolio using Python metrics like Sharpe Ratio, VaR, etc.
Machine learning project that models and forecasts the U.S. Treasury yield curve using real FRED data. Combines Gaussian Process Regression for smooth yield curve fitting and Random Forests for next-day yield forecasting.
Built ARCH(1) and GARCH(1,1) models to forecast financial market volatility, compare predicted vs. realized 5-day rolling volatility, and visualize volatility clustering for risk analysis.
A machine learning project predicting Citi Bank’s stock price using financial and macroeconomic data.
This repository contains a predictive modeling project focused on forecasting Bank of America's (BAC) stock prices using linear regression. It includes data preprocessing, feature engineering (including lag variables and moving averages), model training, evaluation using RMSE and MSE, and visualizations to assess model performance.
Repositories
6Risk analysis of a stock portfolio using Python metrics like Sharpe Ratio, VaR, etc.
Machine learning project that models and forecasts the U.S. Treasury yield curve using real FRED data. Combines Gaussian Process Regression for smooth yield curve fitting and Random Forests for next-day yield forecasting.
In this model, we have calculated 1 day VaR using Monte carlo simulations and variance-covaraince method for a 4 stock portfolio.
Built ARCH(1) and GARCH(1,1) models to forecast financial market volatility, compare predicted vs. realized 5-day rolling volatility, and visualize volatility clustering for risk analysis.
A machine learning project predicting Citi Bank’s stock price using financial and macroeconomic data.
This repository contains a predictive modeling project focused on forecasting Bank of America's (BAC) stock prices using linear regression. It includes data preprocessing, feature engineering (including lag variables and moving averages), model training, evaluation using RMSE and MSE, and visualizations to assess model performance.