Why this lab exists, and how decisions are computed
A software engineer for more than 20 years and passionate about technological revolutions, I have specialized in artificial intelligence over the past two years.
When it comes to financial markets, my knowledge is limited to broad economic principles. That gap is exactly why NeuroTrade Cortex exists: rather than relying on traditional financial intuition, I wanted a full-scale experimental lab to test and evaluate how an autonomous AI performs at portfolio management.
This site aims to provide full transparency into that experiment. Day after day, our algorithmic trader analyzes the market, shortlists opportunities, assesses risk, and manages a virtual capital allocation (paper trading). Here you can follow live:
This project is a technical and educational experiment.
Artificial intelligence is a powerful decision-support tool, but it is by no means infallible. It can misread analysis or face the unpredictable swings of markets. Nothing on this site constitutes investment advice or an invitation to buy or sell financial assets.
This site shows a fictional portfolio. No real capital is committed through the public interface. Orders are simulated after the US close from daily OHLC bars.
The equity curve is rebuilt from daily snapshots (cash + holdings). Configured paper costs filter entry decisions; they are not yet separately deducted from displayed portfolio value. The primary benchmark is the S&P 500 (SPY).
The rating expresses strategic conviction, not a benchmark-relative overweight calculation. The displayed exposure separates the actual weight, planned size and build status; no add is executed automatically.
Buy now: first tranche at the next open, as a % of target size. Wait (pullback/breakout): conditional intent. Hold / wait without an order: conviction without immediate new exposure.
Human-owned caps: per-trade risk, position weight, sector, regime-based exposure, and a temporary halt on excessive drawdown.
