Can you use autoregressive diffusion to generate market data?
What happened
A research intern named Kavish worked on developing a diffusion model for generating market data using an encoder–diffuser architecture. The model predicts the event kind (trade or BBO update) based on the encoded latent and the true event kind. The model generates continuous targets like price, elapsed time, etc., conditioned on the event kind and the encoded latent.
Why it matters
This research could potentially help market data generators, traders, and researchers by providing a tool for generating synthetic market data for testing and analysis purposes. It may also aid in understanding market dynamics and improving trading strategies.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
Show HN: New Cartesia Text-to-Speech ModelIndustry news · 13 Nov 2026Chicago schools to Google – we'd rather lose Search than be forced to accept AIIndustry news · 13 Nov 2026Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026How AI Is Helping Care Teams Get Patients the Right Care, SoonerNVIDIA · 13 Nov 2026This page was collected from blog.janestreet.com and summarised automatically by AIPulsee's pipeline. See how it runs.