Fisher Transform Signals for Price Reversals

Summary

This document describes a Fisher Transform strategy that normalizes price within a recent high-low range, transforms the normalized value, and uses its direction relative to zero to choose long or short exposure. The illustrated calculation applies recursive smoothing and limits the normalized input near the transform’s boundaries. A configurable lookback controls the price range, and an option can reverse the signal direction.

The document supplies a BTC/USDT futures backtest period and parameter defaults, but reports no performance statistics or comparative evidence. It presents turning points as a way to identify reversals, while also noting that parameter choices can create missed or false signals, volatile markets can make turns difficult to judge, and live execution is affected by slippage. The suggested additions—filters, stops, and re-entry rules—are possible refinements, not tested results. The strategy should therefore be treated as an indicator-based hypothesis rather than a demonstrated edge.

Key ideas

• The strategy normalizes price using the recent high and low before applying a Fisher Transform.
• It takes long or short exposure according to whether the smoothed transform is above or below zero.
• A lookback setting affects the normalized range, and the signal direction can be reversed.
• The published backtest setup contains no reported performance results.
• Slippage, volatile conditions, and parameter sensitivity may weaken reversal signals.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.