Exotic Options Pricing & Volatility Modelling
Derivatives research · Barrier, Lookback & Asian options
Analytical proposal for pricing exotic and vanilla derivatives under stochastic volatility — combining real-time volatility surface calculation (LSTM + Gradient Boosting), Monte Carlo simulation + neural networks for path-dependent pricing, reinforcement learning for Barrier knock-in / knock-out triggers, and Quantum Approximate Optimization (QAOA) for high-dimensional exotic pricing problems. Critiqued Black-Scholes assumptions, mapped the $500T derivatives market context, and sized the cost-benefit case to a $4.8M revenue projection.
RL predicts knock-in / knock-out triggers and optimises hedging response.
Neural networks evaluate full historical price paths to maximise payoff.
Deep learning models estimate average-price forecasts under path-dependence.
Sub-second updates targeting <1% pricing error margin.
QAOA applied to high-dimensional exotic pricing — first-class venture differentiator.
Interested in this kind of work?
Get in touch →