AI SuperTrend Clustering Oscillator [LuxAlgo]

Aug 16, 2023

The AI SuperTrend Clustering Oscillator is an oscillator returning the most bullish/average/bearish centroids given by multiple instances of the difference between SuperTrend indicators.

This script is an extension of our previously posted SuperTrend AI indicator that makes use of k-means clustering. If you want to learn more about it see:

🔶 USAGE



The AI SuperTrend Clustering Oscillator is made of 3 distinct components, a bullish output (always the highest), a bearish output (always the lowest), and a "consensus" output always within the two others.

The general trend is given by the consensus output, with a value above 0 indicating an uptrend and under 0 indicating a downtrend. Using a higher minimum factor will weigh results toward longer-term trends, while lowering the maximum factor will weigh results toward shorter-term trends.



Strong trends are indicated when the bullish/bearish outputs are indicating an opposite sentiment. A strong bullish trend would for example be indicated when the bearish output is above 0, while a strong bearish trend would be indicated when the bullish output is below 0.



When the consensus output is indicating a specific trend direction, an opposite indication from the bullish/bearish output can highlight a potential reversal or retracement.

🔶 DETAILS

The indicator construction is based on finding three clusters from the difference between the closing price and various SuperTrend using different factors. The centroid of each cluster is then returned. This operation is done over all historical bars.

The highest cluster will be composed of the differences between the price and SuperTrends that are the highest, thus creating a more bullish group. The lowest cluster will be composed of the differences between the price and SuperTrends that are the lowest, thus creating a more bearish group.

The consensus cluster is composed of the differences between the price and SuperTrends that are not significant enough to be part of the other clusters.

🔶 SETTINGS

• ATR Length: ATR period used for the calculation of the SuperTrends.
  
• Factor Range: Determine the minimum and maximum factor values for the calculation of the SuperTrends.
  
• Step: Increments of the factor range.
  
• Smooth: Degree of smoothness of each output from the indicator.
  

🔹 Optimization

This group of settings affects the runtime performances of the script.

• Maximum Iteration Steps: Maximum number of iterations allowed for finding centroids. Excessively low values can return a better script load time but poor clustering.
  
• Historical Bars Calculation: Calculation window of the script (in bars).