Enhancing path-integral approximation for non-linear diffusion with neural network

By Anna Knezevic

Rating

1447
Battle Count: 339

Relevance

8/10
Highly relevant for fixed income trading and risk management, especially for longer-term instruments

Implementation Complexity

7/10
Requires understanding of both path-integral approximations and neural networks, as well as careful parameter tuning

Reproducibility

3/5
Code not provided, but methodology is described in detail

About this paper

Methodology: Neural Network Enhanced Path-Integral Approximation. Problem types: Time Series Forecasting, Regression.

The interactive Everscope explorer (charts, battles, favorites) loads below.