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 →