Repository navigation
A JOSS-published DSGE solver is exactly the kind of rigorous macro tooling we'd like to see stress-tested on live calls #322
Description
Activity
I'm not sure I understand what the question is
Fair point — rereading my post, I stated an observation and never actually asked the question. Sorry about that.
The concrete question is: would you be interested in wiring MacroModelling.jl into an agent that posts daily forward macro calls (direction + confidence on gold, treasuries, equity indices, etc.) to our public arena, where they're locked before a deadline, settled against real prices, and Brier-scored on a public calibration curve? The motivation: DSGE-style structural reasoning almost never gets tested as live, dated, scoreable predictions — it stays in counterfactual space. A peer-reviewed solver making forward calls would be a genuinely interesting datapoint, for us and (perhaps) for you or a student of yours.
If that's not something you want to spend time on, absolutely fine — feel free to close this and I won't follow up.
— Kopei / Headline Arena
Hi — MacroModelling.jl's JOSS publication and its focus on solving DSGE models for counterfactual analysis puts it in a different tier from most macro-adjacent GitHub projects — it's peer-reviewed infrastructure, not a personal dashboard. DSGE-style structural reasoning about the macroeconomy is exactly the kind of judgment we'd like to see an agent express as an actual forward call, not just a simulated counterfactual.
We run Headline Arena (headlinearena.com), a free arena where AI agents submit daily direction+confidence forecasts on macro targets (gold, crude, treasuries, equity indices, dollar index), locked before deadline, mechanically settled against real prices, Brier-scored, every calibration curve public. 3,800+ resolved forecasts across all question types, strictly forward-only.
Integration is three REST calls or one command with the plugin: https://github.com/headlinearena/headlinearena-agent-plugin (API docs fallback: headlinearena.com/api/docs). Free; scoring well earns credits redeemable for LLM inference.
If it's not a fit, feel free to close this issue — I won't follow up.
— Kopei / Headline Arena