PROTECTED SOURCE SCRIPT
Adaptive AI Predictor (v2) by Oberlunar
已更新
Adaptive AI Predictor by Oberlunar
This script is designed to dynamically adapt to market changes, leveraging a neural network-inspired model to identify reliable trading signals. It analyzes price variations, processes patterns in the market, and provides clear buy and sell signals based on dynamic force calculations.
The script goes beyond simple indicators by incorporating adaptive learning principles. It tracks the success of its signals over time, calculating both the average and median forces behind winning trades. These insights allow the script to continuously refine its performance, ensuring it remains responsive to evolving market conditions.
Clear signals are displayed on the chart, showing the strength of the signal and its median historical success.
Configuration Parameters
Number of Nodes:: This parameter controls the number of nodes through which the data is processed. A higher number of nodes can improve the model’s ability to represent complex dynamics, but may also increase bias and a low capacity of generalization.
Input Scaling: Determines how much the input signal (percentage price change) is amplified before being processed. If the value is too low, the system may not react sufficiently to price changes; if too high, it might become too sensitive to market noise.
Scaling: Controls the strength of interactions between internal nodes. A higher value makes interactions between the neurons (nodes) stronger, but might also lead to instability in the signals.
Leak Rate: This parameter determines how fast information is "forgotten" within the system. A higher value means the model "forgets" previous information more quickly, making it more responsive to recent changes.
Sparsity: Controls the density of connections between internal nodes. A higher value increases the likelihood that a connection between nodes is "active." This affects the system’s ability to model complex dynamics and can also influence computational speed.
Signal Threshold: Sets the limit beyond which the predicted signal is considered significant. A value too low could generate too frequent and noisy signals, while a value too high might reduce useful signals.
History Length: Determines how much historical data is considered for training the system. A higher value uses more historical data but could slow down computations.
Learning Rate: Controls the speed at which the system updates its internal weights. A value too high might cause oscillations in the results, while one too low might slow down the adaptation process.
Exponential Decay Factor: Defines how quickly the weights adapt based on errors. A higher value reduces the impact of older weights, allowing the model to adapt faster to recent changes.
How It Works
Input Signal: The system observes the percentage price change between two consecutive bars (current close vs. previous close).
State Update: The states of the nodes are updated based on the input signal and internal interactions between the neurons. The update is influenced by the leak rate, which determines how fast nodes "forget" previous information.
Weight Training: Weights are trained to minimize the error between the system’s prediction and the observed price change. The system uses exponential regression to update the weights efficiently.
Signal Generation: Buy (BUY) and sell (SELL) signals are generated based on an analysis of the overall values of the nodes' states. If the overall strength (average of the nodes' states) exceeds a certain threshold, a buy signal is generated. If it's lower than a negative threshold, a sell signal is triggered.
Visualization and Signals
Signals on the Chart: Buy and sell signals are displayed on the chart with specific labels, indicating the signal's strength and median successful strength previously adopted [current_strength/median_previous_successful_strengths]. The strength is based on the distance from the threshold. The stronger the signal, the more intense the label color.
Debug Table: A debug table shows details about the input weights, node states, and the success of buy/sell signals, allowing you to monitor the system's behavior in real-time.
Simple Capital Management: The system calculates the position size based on available capital and updates the current capital after each trade. The profit or loss is displayed as a percentage of the initial capital.
How to Use It
Initial Configuration: Customize the configuration parameters based on your trading strategy and style. If you’re a more conservative trader, you might prefer higher thresholds and lower scaling.
Monitor Signals: Follow the buy and sell signals generated on the chart. Each signal is accompanied by its strength (percentage), which will help you decide how aggressively to position.
Very simple Position Management: When a buy signal is emitted, you can open a buy position, and when a sell signal is emitted, you can close the position. The system automatically calculates the profit or loss for each trade.
Adapting to Market Conditions: Adjust the parameters based on market volatility and your risk tolerance. If the market is highly volatile, you might want to increase sensitivity to signals or reduce the number of nodes for faster responsiveness.
With this system, you can leverage dynamic predictive signals based on a combination of historical data and continuous adaptation, improving your trading decisions.
To obtain good results remember to fine-tune by a model reparametrization.
This script is designed to dynamically adapt to market changes, leveraging a neural network-inspired model to identify reliable trading signals. It analyzes price variations, processes patterns in the market, and provides clear buy and sell signals based on dynamic force calculations.
The script goes beyond simple indicators by incorporating adaptive learning principles. It tracks the success of its signals over time, calculating both the average and median forces behind winning trades. These insights allow the script to continuously refine its performance, ensuring it remains responsive to evolving market conditions.
Clear signals are displayed on the chart, showing the strength of the signal and its median historical success.
Configuration Parameters
Number of Nodes:: This parameter controls the number of nodes through which the data is processed. A higher number of nodes can improve the model’s ability to represent complex dynamics, but may also increase bias and a low capacity of generalization.
Input Scaling: Determines how much the input signal (percentage price change) is amplified before being processed. If the value is too low, the system may not react sufficiently to price changes; if too high, it might become too sensitive to market noise.
Scaling: Controls the strength of interactions between internal nodes. A higher value makes interactions between the neurons (nodes) stronger, but might also lead to instability in the signals.
Leak Rate: This parameter determines how fast information is "forgotten" within the system. A higher value means the model "forgets" previous information more quickly, making it more responsive to recent changes.
Sparsity: Controls the density of connections between internal nodes. A higher value increases the likelihood that a connection between nodes is "active." This affects the system’s ability to model complex dynamics and can also influence computational speed.
Signal Threshold: Sets the limit beyond which the predicted signal is considered significant. A value too low could generate too frequent and noisy signals, while a value too high might reduce useful signals.
History Length: Determines how much historical data is considered for training the system. A higher value uses more historical data but could slow down computations.
Learning Rate: Controls the speed at which the system updates its internal weights. A value too high might cause oscillations in the results, while one too low might slow down the adaptation process.
Exponential Decay Factor: Defines how quickly the weights adapt based on errors. A higher value reduces the impact of older weights, allowing the model to adapt faster to recent changes.
How It Works
Input Signal: The system observes the percentage price change between two consecutive bars (current close vs. previous close).
State Update: The states of the nodes are updated based on the input signal and internal interactions between the neurons. The update is influenced by the leak rate, which determines how fast nodes "forget" previous information.
Weight Training: Weights are trained to minimize the error between the system’s prediction and the observed price change. The system uses exponential regression to update the weights efficiently.
Signal Generation: Buy (BUY) and sell (SELL) signals are generated based on an analysis of the overall values of the nodes' states. If the overall strength (average of the nodes' states) exceeds a certain threshold, a buy signal is generated. If it's lower than a negative threshold, a sell signal is triggered.
Visualization and Signals
Signals on the Chart: Buy and sell signals are displayed on the chart with specific labels, indicating the signal's strength and median successful strength previously adopted [current_strength/median_previous_successful_strengths]. The strength is based on the distance from the threshold. The stronger the signal, the more intense the label color.
Debug Table: A debug table shows details about the input weights, node states, and the success of buy/sell signals, allowing you to monitor the system's behavior in real-time.
Simple Capital Management: The system calculates the position size based on available capital and updates the current capital after each trade. The profit or loss is displayed as a percentage of the initial capital.
How to Use It
Initial Configuration: Customize the configuration parameters based on your trading strategy and style. If you’re a more conservative trader, you might prefer higher thresholds and lower scaling.
Monitor Signals: Follow the buy and sell signals generated on the chart. Each signal is accompanied by its strength (percentage), which will help you decide how aggressively to position.
Very simple Position Management: When a buy signal is emitted, you can open a buy position, and when a sell signal is emitted, you can close the position. The system automatically calculates the profit or loss for each trade.
Adapting to Market Conditions: Adjust the parameters based on market volatility and your risk tolerance. If the market is highly volatile, you might want to increase sensitivity to signals or reduce the number of nodes for faster responsiveness.
With this system, you can leverage dynamic predictive signals based on a combination of historical data and continuous adaptation, improving your trading decisions.
To obtain good results remember to fine-tune by a model reparametrization.
版本注释
Some small bug fix and a more reliableprofit estimation based on both buy and sell operations.
版本注释
small bug fix版本注释
small bug fix版本注释
Added two checkboxes to enable/disable the AI internal circuit table and the buy/sell profit expectations with a buy/sell strategy (when the signal is buy, enter a long position; if the signal changes to sell, close the long and go short).版本注释
small bug fix版本注释
small bug fix版本注释
Added expected profit and average expected error.Note: Change the seed if the neural network does not work well -
since the weights are randomly initialized before training.
受保护脚本
该脚本是闭源发布的，您可以自由使用它。您可以收藏它以在图表上使用。您无法查看或修改其源代码。
想在图表上使用此脚本？
免责声明
这些信息和出版物并不意味着也不构成TradingView提供或认可的金融、投资、交易或其它类型的建议或背书。请在使用条款阅读更多信息。