Coursework, projects, and datasets from the MSc in Financial Engineering (MScFE) program at WorldQuant University.

A comprehensive end-to-end deep learning finance project implementing tactical asset allocation strategies using LSTM neural networks to forecast multi-asset ETF returns and generate dynamic portfolio rebalancing signals.

Forecast multi-asset ETF returns and generate dynamic portfolio rebalancing signals using LSTM neural networks for tactical asset allocation.

A quantitative finance toolkit addressing model reliability through hyperparameter optimization (GridSearch/LassoCV), bias-variance tradeoff analysis, and ensemble learning (Random Forests and Stacking) applied to S&P 500 and Sector ETF data.

Modern portfolio optimization using constrained Kelly, HRP, K-Fold cross-validation, and Marčenko-Pastur denoising to improve risk-adjusted returns.

A quantitative finance project that explores the intersection of traditional technical analysis and alternative data. It replicates academic methodologies for predicting stock market movements using classification models, and demonstrates the practical application of NLP sentiment analysis (VADER) in financial modeling.

A Python-based analysis of fundamental econometric challenges, including Omitted Variable Bias (OVB), sensitivity to outliers, model selection criteria, elasticity, and time series stationarity, utilizing both simulated environments and empirical real-world financial data.

An end-to-end quantitative portfolio management project built in Python. This repository explores advanced asset allocation techniques, including Mean-Variance Optimization (MVO), Fama-French 5-Factor style analysis, Monte Carlo simulations, and the Black-Litterman model.

A comprehensive Python framework for financial derivative valuation using numerical methods. This project implements Binomial and Trinomial trees to price European and American options, analyzes sensitivities (Greeks), and simulates dynamic delta hedging strategies.

A comprehensive quantitative handbook applying machine learning methodologies (Regularization, Clustering, PCA, and Decision Trees) to real-world financial data for market regime detection and trading strategy optimization.

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

An advanced Python framework for pricing financial derivatives beyond Black-Scholes using the Heston Stochastic Volatility Model and the Merton Jump Diffusion Model. The project evaluates European, American, and Barrier options, analyzes strike sensitivities, and computes Greeks using Monte Carlo simulations.

Applies econometric and machine learning techniques to financial time series analysis. Uses PCA for feature extraction, Engle-Granger cointegration for non-stationarity, Ridge Regression for multicollinearity, and Markov Switching Autoregression for regime detection with Yahoo Finance and FRED data.

A quantitative finance project implementing stochastic volatility models (Heston, Bates) and interest rate diffusion models (CIR) to price Over-The-Counter (OTC) derivatives.

A quantitative finance project utilizing Hidden Markov Models (HMM) to infer market volatility regimes from the VIX index and dynamically rotate assets among SPY, TLT, and GLD.

An advanced quantitative finance toolkit expanding "Marketing Alpha" strategies. Applies non-linear machine learning models (LDA, SVM, Neural Networks) and refined linear methods to tackle complex financial time series forecasting and market regime classification.

Quantitative analysis of financial time-series data, featuring Nelson-Siegel yield curve calibration, cubic spline interpolation, and PCA/SVD dimensionality reduction for risk factor decomposition.

An investigation into the application of Deep Learning architectures (MLP, LSTM, and CNN via Gramian Angular Fields) to predict Bitcoin directional returns, focusing on a rigorous forensic analysis of data leakage.