CalibratedDecisions.

Repo · Trading & finance

Cda Abm AI Agents

Mesa market testbed pitting zero-intelligence traders against Jev archetype agents, with paired Monte Carlo stats, a live dashboard, and a…

Open github.com ↗

From the repository

Replicating Gode & Sunder (1993) Continuous Double Auction with TypeSafe AI Jev agents. Compares canonical ZI-C heuristics against stochastic choice AI Jev brains. Results led to compressing price variance by 43% while matching 97% allocative efficiency. Includes real-time web interface & Jupyter Notebook econometrics.

How builders describe it

Mesa market testbed pitting zero-intelligence traders against Jev archetype agents, with paired Monte Carlo stats, a live dashboard, and a pre-rendered econometrics notebook.

The decision Jev makes

Choose a trade action, rate a signal, or label a transaction.

Where it fits

Experimental trading loops, market signals and money tools where each step is a bounded decision: buy, sell, hold, or which category a transaction belongs to. All 77 trading & finance projects →

Related projects