A Practical Guide to G-LSM: Improving High-Dimensional Option Pricing with Minimal Overhead
24 Sept 2025
Solving high-dimensional option pricing: G-LSM leverages Hermite polynomials and gradients to achieve a 10x accuracy boost over LSM.
The Price of Friction: How Transaction Costs Change the Strategic Trading Game
23 Sept 2025
This paper extends the Nash equilibrium model to markets with transaction costs, characterizing the solution via a system of FBSDEs.
Nash Equilibrium and Revealed Risk Exposure with Endogenous Price Impact
23 Sept 2025
We derive a closed-form Nash equilibrium where strategic investors alter market returns by revealing a different risk exposure than their true one.
Your Trades Move the Market: Rethinking Equilibrium When Every Order Has an Impact
23 Sept 2025
This work models a market equilibrium where investor price impact amplifies the effect of transaction costs, providing a closed-form solution.
Validating Hyperparameters and a Weekly Re-training Strategy for DRL Option Hedging
26 Aug 2025
This research validates a weekly re-trained DRL agent, showing it outperforms static models & Black-Scholes for practical American option hedging.
Don't Just Train Your AI, Re-Train It: The Weekly Workout Plan for a Smarter Option Hedge
26 Aug 2025
This methodology details how to train and test DRL agents for American option hedging, introducing a novel weekly re-training strategy using Chebyshev pricing.
Avoiding the Pitfalls: A Guide to the Current State of DRL Option Hedging Research
26 Aug 2025
This review of DRL hedging literature highlights the need for hyperparameter analysis, especially for real-world American option applications.
How Weekly AI Training Is Beating a Nobel Prize-Winning Formula
26 Aug 2025
This paper makes Deep Reinforcement Learning practical for hedging American options by optimizing hyperparameters and using a weekly re-training strategy.
Efficient Price and Greeks Computation for American Options via Gradient-Enhanced LSM
12 Aug 2025
This article introduces G‑LSM, a sparse Hermite polynomial LSM variant using gradient info for efficient, accurate high‑dimensional American option pricing.