Stochastic Oscillator Strategy with Trend and RSI-Based Signal Filters

Summary

This strategy uses a smoothed Stochastic oscillator to identify potential overbought and oversold entries, with a 200-period simple moving average serving as a trend filter for additional entry conditions. The description also presents an AI signal as a filter and specifies fixed profit and loss distances. It lists oscillator thresholds and smoothing settings, along with a BTC futures backtest configuration, but reports no performance results.

There is an important gap between the description and implementation: the source's purported recurrent neural network signal is a simple RSI comparison, and the oscillator crossover entries do not require that signal or the moving-average condition. The code also creates separate entries for these rule sets. The document cautions that oscillator signals can be unreliable, fixed exits may not suit changing volatility, and model quality is uncertain; the supplied code does not establish evidence of AI-driven performance.

Key ideas

• Smoothed Stochastic crossovers generate entries when the oscillator reaches specified extreme zones.
• A 200-period simple moving average is used in a separate set of trend-filtered entry conditions.
• The code's purported AI signal is based on RSI rather than a recurrent neural network.
• Fixed profit and loss distances may not adapt to changing volatility.
• The backtest settings are provided without reported performance statistics.

Tags

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