Enter a ticker
Use liquid symbols first. Start with five years of history to give cycles and macro proxies enough room.
Operator guide
How to read the model
Inv-Wave blends price waves, nature-inspired formation physics, company shape, market coast, macro weather, and risk into a decision layer. Treat it as a research cockpit: it gives a structured setup, levels, and validation evidence, not certainty.
Workflow
Use liquid symbols first. Start with five years of history to give cycles and macro proxies enough room.
The default 30 trading days is a swing horizon. Shorter horizons emphasize wave state; longer horizons emphasize drift and volatility.
Use the action, setup score, target, pullback, breakout, invalidation, data reliability, and reasons before reading secondary scores.
Run the backtest, then compare directional accuracy, information coefficient, error, interval hits, and hidden-wave hit rate.
Buy guidance
Forecast, setup score, risk, and formation physics are aligned enough for the model to support current-price exposure.
The setup is constructive but not dominant. The model prefers smaller sizing or waiting for breakout confirmation.
The thesis is constructive, but the current wave is extended. Pullback entry is the cleaner modeled risk point.
The physics layer detects stored energy or precursor rhythm, but confirmation from price, macro, or risk is incomplete.
No decisive edge. The model is saying the stock may be interesting, but not actionable yet.
Downside pressure, risk, or poor composite quality dominates. This is a defensive posture, not a buy signal.
Model layers
3D surface
High ridges represent stronger formation energy from price normalization, rhythm, stored energy, and wave concentration.
Cyan leans toward organized energy, amber toward stored/ignition energy, and magenta toward break stress.
Drag the surface to inspect structure. It does not auto-spin, so visual motion does not imply market motion.
Validation
Limits
This is experimental quantitative research software. It can miss regime shifts, bad data, news shocks, liquidity events, and structural breaks. Do not treat outputs as personalized financial advice. The useful habit is iteration: analyze, backtest, compare, refine thresholds, and keep position sizing outside the model.