Strong, persistent movers versus noisy momentum spikes.
Vectors
Monstra Vectors (Core)
Coming SoonOpen-source implementation, published as-is.
Uses
- Python 3.12+
Run It Yourself
- Market data — bring your own
Adaptive Universe Engine
Coming SoonOpen-source implementation, published as-is.
Uses
- Python 3.12+
- Monstra Vectors (Core)Coming Soon
Every stock in Monstra's universe is assigned a Vector. Each Vector is built from that stock's own daily price and volume history across windows from one week to five years, covering return, volatility, trend, drawdown, performance versus the broader market, and liquidity. Those raw measures are normalized to a fixed 0 to 1 scale for that ticker alone, not ranked against other stocks that day, then combined into the composite scores shown below, like momentum, trend quality, and downside awareness. Each algorithm reads those scores to find the stocks it wants.
Market leaders that are either resilient or dangerously volatile.
High-upside, high-variance names versus dependable compounders.
Ticker fit snapshot
Bot fits and vector dimensions for the selected ticker.
Fresh 10-stock vector universe
No algorithm selected - each click ranks purely by the selected tag scores, after any sector and industry filters are applied.