Discussion about this post

User's avatar
Matthew's avatar

The regime-mapping framework is the right foundation. Most macro research tells you what happened. The useful version tells you where you are in the cycle and what that implies for positioning.

Building AI infrastructure around that problem is where I am spending most of my time right now too. The hard part is not the model. It is getting the signal inputs clean enough that the system does not just pattern-match noise.

Curious how you are handling the liquidity layer specifically. That variable tends to lead everything else.

No posts

Ready for more?