New AI Predicts Sudden Jumps in Stocks and Weather
This could help you avoid financial surprises and plan for extreme events.
We study the problem of learning transition kernels for time-homogeneous jump-diffusion processes using conditional diffusion models, with the goal of generating new sample paths from training data consisting of N independent trajectories observed on a high-frequency discrete time grid. On the theoretical side, we establish non-asymptotic bounds for the conditional score estimation error and for the KL divergence between the laws of the true and generated discretely observed paths.
On the numerical side, we first evaluate our method on synthetic data to assess the theoretical findings and benchmark its performance against the approach of Gao et al. (2025). We then apply our method to real-world data and investigate its performance on a probabilistic forecasting task.
- AI can now learn to predict sudden jumps in data, like stock crashes or weather shifts.
- It uses a diffusion model, similar to AI image generators, but for time-based numbers.
- This could lead to better risk warnings, but it's still experimental and not yet available.
Why It Matters
Better predictions of sudden events could save money and lives by giving early warnings.