Quantitative Trading,
Mathematically Proven.
A quantitative research project applying stochastic calculus, XGBoost, and deep learning to predict high-frequency market micro-structures.
Core Mathematical Concepts
Stochastic Processes
The architecture of randomness and probability in financial markets.
The Martingale
Understanding perfect mathematical equilibrium and 'fair' games.
Brownian Motion
The continuous random walk and the foundations of quantitative finance.
Geometric Brownian Motion (GBM)
The engine of Wall Street and how quants model the stock market.
Mathematical Modeling
Leveraging stochastic calculus, differential equations, and probability theory to model market micro-structures and mean reversion.
Machine Learning
Predicting binary market outcomes using XGBoost and LSTM recurrent neural networks trained on order book imbalances and log returns.
Dynamic Risk Sizing
Executing statistical edges on Polymarket and crypto feeds using fractional Kelly Criterion algorithms to prevent ruin and optimize growth.