Signal Settings
Overview
The Signal Settings for Lune Elara allow you to control the generation and behavior of trade entry signals. These settings provide a high degree of customization, letting you fine-tune the strategy’s responsiveness by leveraging an advanced, AI-driven engine. By configuring the prediction model, selecting market features, and adjusting sensitivity, you can tailor the signal logic to fit your specific trading style and the market you are analyzing.
Signal Generation Logic
To protect our proprietary algorithms, the exact mechanics of the signal logic are not disclosed. However, the conceptual approach can be understood as follows:
Lune Elara utilizes a sophisticated, adaptive AI model powered by an advanced machine learning engine to identify trading opportunities. The strategy dynamically builds a feature vector from a wide range of market characteristics—such as volatility, trend memory, and order flow—based on your selections.
The model continuously learns and updates its understanding of how these features influence future price movements, allowing it to adapt to changing market conditions. It can optionally use a reinforcement learning framework to further refine its decision-making based on past performance. This adaptive approach ensures the signal logic remains effective and relevant as market behavior changes. All signals are confirmed on the close of a price bar to ensure they do not repaint.
Settings
The following settings control the core logic of the signal engine.
General Settings
Long Trades
Enables or disables the generation of long (buy) signals.
Short Trades
Enables or disables the generation of short (sell) signals.
Prediction & Sensitivity
These settings define the AI's prediction target and its overall responsiveness.
Prediction Target Mode
Configures what the AI model predicts. "Standard Return" predicts the next bar's return, while "Maximum Favorable Excursion" predicts directional profit potential.
Standard Return
Maximum Favorable Excursion
Prediction Horizon
Sets the number of bars ahead for the AI to predict (only used in MFE mode).
Range: 1 - 50
Recommended: 3 - 10
Minimum Desired Move
Sets a volatility-normalized minimum move required for a signal, using the Average True Range (ATR). A value of 1.5 means the predicted move must be at least 1.5x the current ATR.
Range: 0.1 - 10.0
Recommended: 0.8 - 2.0
Signal Sensitivity
Controls the overall responsiveness and frequency of signals. Lower values are more sensitive and produce more signals.
Range: 0.1 - 10.0
Recommended: 1.0 - 3.0
Learning Rate
Controls how quickly the AI model adapts to new market data. Lower values result in slower, more stable adaptation.
Range: 0.01 - 0.50
Recommended: 0.03 - 0.10
Analysis Lookback Window
Sets the size of the sliding data window the AI model uses for its analysis. A shorter window adapts faster to regime changes.
Range: 50 - 2000
Recommended: 300 - 800
Dynamic Feature Selection
Select up to eight market features for the AI model to analyze. The model will dynamically weigh the importance of each selected feature.
Feature 1-8 Type
Selects the type of market feature to analyze. Each option captures a different market characteristic to enhance prediction accuracy.
Disabled, Return Smoothing, Volatility Analysis, Distribution Skewness, Distribution Kurtosis, Trend Memory, Price Efficiency, Volume Analysis, Flow Analysis, Volatility Regimes, Market Efficiency, Regime Detection, Pattern Detection, Change Detection, Price Filtering, Velocity Tracking, Trend Filtering, State Tracking, Momentum Analysis, Sharpe Ratio, Win Rate, Profit Factor
Feature 1-8 Lookback
Sets the number of bars used for the feature's calculation. A lower value is more responsive to recent data.
Range: 1 - 2000
Recommended: 50 - 250
Advanced Signal Settings
These settings enable advanced, experimental systems for signal processing. Use at your own risk.
Reinforced Learning
Enables a system that adjusts its behavior based on market feedback and outcomes.
On/Off Toggle
Reinforced Learning Rate
Controls the balance between exploration (trying new actions) and exploitation (using known profitable actions).
Range: 0.01 - 0.5
Recommended: 0.05 - 0.2
Reinforced Learning Lookback
Sets the period for the adaptive learning history and feedback analysis.
Range: 1 - 2000
Recommended: 250 - 1000
Skipped Signal Evaluation Bars
Sets the number of bars to wait before evaluating the outcome of a skipped signal for reinforcement learning.
Range: 1 - 100
Recommended: 10 - 30
Target Sharpe
Sets the performance threshold when using the Sharpe Ratio
feature.
Range: 0.01 - 5.0
Recommended: 1.0 - 2.5
Target Win Rate
Sets the performance threshold when using the Win Rate
feature.
Range: 0.01 - 0.99
Recommended: 0.40 - 0.75
Target Profit Factor
Sets the performance threshold when using the Profit Factor
feature.
Range: 1.0 - 5.0
Recommended: 1.2 - 2.5
Price Filtering Process Noise
Controls the noise parameter for the Kalman Filter calculations used in Price Filtering
.
Range: 0.001 - 0.1
Recommended: 0.005 - 0.02
Pattern Detection Sensitivity
Adjusts the sensitivity for Pattern Detection
and Regime Detection
features.
Range: 0.01 - 1.0
Recommended: 0.05 - 0.2
Best Practices & Usage
Select Diverse Features: When choosing features, select a diverse set that captures different aspects of the market (e.g., one for trend, one for volatility, one for volume). This allows the model to build a more robust understanding.
Balance Sensitivity and Confirmation: Lowering
Signal Sensitivity
will generate more signals but may also increase the number of false positives. Higher values provide stronger confirmation but may result in fewer trading opportunities. Find a balance that suits your risk tolerance.Adjust Lookbacks for Your Timeframe: If you are trading on a lower timeframe, consider using shorter
Lookback
periods to make the strategy more responsive. For higher timeframes, longerLookback
periods can provide more stable and reliable signals.Use MFE for Clearer Directional Bias: The "Maximum Favorable Excursion"
Prediction Target Mode
can be effective for strategies that aim to capture larger, more directional moves, as it focuses on profit potential rather than just the next bar's return.Start with Recommended Values: The recommended values provide a solid starting point for most markets. Use them as a baseline and then carefully adjust them based on the specific asset and timeframe you are trading.
Tune One Thing at a Time: When optimizing the settings, adjust only one parameter at a time. This will help you clearly understand the effect of each change on the strategy's performance during backtesting.
Last updated
Was this helpful?