P-Signal Reversals from a Normalized Statistical Indicator
Summary
The P-Signal strategy turns recent price-change statistics into a bounded indicator using a Gaussian error-function mapping. It uses moving averages and standard deviations over a configurable sample, then smooths the resulting signal. A change in direction while the signal is beyond a configurable dead band triggers a reversal entry: a falling positive signal opens short, and a rising negative signal opens long.
Cardinality controls the sample size, while the dead-band setting can suppress some trades; the source also includes a start-date input. The document proposes using larger samples, volume checks, multiple timeframes, and stop losses to address sensitivity to outliers and reversal risk. It provides BTC/USDT futures backtest settings for a one-month interval, but no performance results or validation evidence. The approach therefore offers a statistical signal construction and entry rule, not proof that the strategy is profitable or robust.
Key ideas
- The indicator maps moving-average and standard-deviation statistics of price changes to a bounded signal.
- A falling signal above the dead band triggers a short entry.
- A rising signal below the negative dead band triggers a long entry.
- Sample size and dead-band settings affect sensitivity and trading frequency.
- The stated backtest interval has no reported results, and outliers may distort the signal.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.