Corpus ID: 196622484

Neural network regression for Bermudan option pricing

@article{Lapeyre2019NeuralNR,
  title={Neural network regression for Bermudan option pricing},
  author={B. Lapeyre and J. Lelong},
  journal={arXiv: Probability},
  year={2019}
}
  • B. Lapeyre, J. Lelong
  • Published 2019
  • Mathematics, Economics
  • arXiv: Probability
  • The pricing of Bermudan options amounts to solving a dynamic programming principle, in which the main difficulty, especially in high dimension, comes from the conditional expectation involved in the computation of the continuation value. These conditional expectations are classically computed by regression techniques on a finite dimensional vector space. In this work, we study neural networks approximations of conditional expectations. We prove the convergence of the well-known Longstaff and… CONTINUE READING
    Solving high-dimensional optimal stopping problems using deep learning
    18
    Differential Machine Learning
    Pricing and hedging American-style options with deep learning
    5
    Theoretical Guarantees for Learning Conditional Expectation using Controlled ODE-RNN
    1

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 38 REFERENCES
    An analysis of a least squares regression method for American option pricing
    293
    Number of paths versus number of basis functions in American option pricing
    144
    Valuing American Options by Simulation: A Simple Least-Squares Approach
    2761
    Deep Optimal Stopping
    63
    Pricing early-exercise and discrete barrier options by fourier-cosine series expansions
    239