KILLED · no edge
Hypothesis
Bullish/bearish divergence between price and the Relative Strength Index precedes reversals.
Math
$$ \text{RSI} = 100 - \frac{100}{1 + \overline{\text{gain}}/\overline{\text{loss}}} $$
Method
Algorithmic divergence detection (price extreme vs RSI extreme), forward-return test across 50 symbols, costs applied — removing the human eye that usually selects only the winners.
Results
| Divergences detected | thousands |
| Forward-return edge | ≈ 0 |
| Survivorship in manual examples | severe |
Mechanized and tested honestly across all occurrences, RSI divergence has no forward edge. Its reputation comes from hand-picked chart examples (only the ones that worked get screenshotted). Killed.
Any chart pattern looks predictive when you only show the cases where it worked. Detect it algorithmically over everything, then count.