A Range-Correlation Heuristic for Moving-Average Trend Signals

Summary

The document describes a strategy that combines a moving-average crossover with a binary indicator based on whether consecutive bar ranges are positively correlated. It smooths that indicator and uses a threshold to permit long entries when price crosses above a longer moving average, or short entries when price crosses below it. The write-up presents this as an AI-based forecast using multiple time horizons and a future-price probability.

The supplied source does not substantiate that framing. It contains no trained AI model, and the plotted comparison uses a lagged close rather than a future close. The stated probability series is not used in the entry rules; several described multi-period range calculations are also absent from the implementation. Published settings cover BTC/USDT futures over about a year of daily bars, but no results are reported. These discrepancies, along with the document’s own cautions about overfitting and parameter risk, make the strategy difficult to evaluate as a predictive method.

Key ideas

• The implemented entry rules combine a smoothed positive range-correlation indicator with crossings of a long-period moving average.
• The source does not implement a trained AI model despite the strategy’s description as AI-driven.
• The plotted close comparison uses a lagged observation, and its probability series does not govern entries.
• The described multi-period range calculations are not fully reflected in the supplied source.
• The document reports BTC/USDT futures backtest settings but gives no performance results.

Tags

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