Alpha Bollinger Band Trading Strategy

The Entropy Alpha Strategy is an exclusive trading approach based on the principles of the Entropy System, which revolves around probability distribution theories, with Bollinger Bands serving as its primary tool.

Although We are not going into deep of the strategies’ definitive principles but lets discuss the basic core of the strategy to show that how new strategies can be modelled with the principles of the Entropy System.

The 3BB (3 Bollinger Bands) strategy is a trading approach that combines Bollinger Bands with specific candlestick patterns to minimize losses and capitalize on high-confidence breakout opportunities, particularly when the 3rd candle in a formation indicates a potential reversal or downward movement. 

In the chart example featuring Grasim, you can observe two successful 3BB trades that unfolded seamlessly.

Upon zooming out, the broader perspective reveals a discernible uptrend in the market.

The 3BB strategy excels in offering sell entry signals at the market’s peaks, effectively capturing mean reversion trades, and then providing exit signals near the median Bollinger Band. But, after a period of consolidation, the stock once again breaks out of the previous resistance and continues on the path of Uptrend. 

Now the question ariese – 

  1. So, What if We enter a Buy trade at the end of the 3BB trade?
  2. Or, What if We can predict that the 3BB trade will hit the stop loss and will resume the Uptrend?

What is the Entropy Alpha Strategy?

The Entropy Alpha Strategy employs advanced Machine Learning techniques to augment its trading capabilities. This innovative approach leverages historical trade data from the 3BB Strategy to make informed trading decisions.

Identifying Profitable Trades on Exit:

The Machine Learning model sifts through the trade history to pinpoint trades that would have been more profitable if one had entered them at the time of the original trade’s exit. This valuable insight helps traders recognize opportunities to maximize profits by timing their entries strategically.

Predicting Trades at Risk of Hitting Stop Loss:

Equally important, the model identifies trades with a high probability of hitting the stop loss. This risk assessment empowers traders to exercise caution or consider alternative strategies when approaching potentially risky trades.


The Entropy Alpha Strategy harnesses the predictive power of Machine Learning to refine trading decisions. Two notable models play pivotal roles in this strategy:

Machine Learning Models in the Entropy Alpha Strategy

Regression Analysis:

Regression analysis is a core component of the Machine Learning framework employed within the Entropy Alpha Strategy. This statistical method is used to examine relationships between variables, making it an invaluable tool for identifying profitable trades and managing risk.

  1. Profitable Trade Identification: Through regression analysis, the model scrutinizes historical trade data from the 3BB Strategy. It assesses factors such as entry and exit points, trade durations, and market conditions to determine which trades would have been more profitable if the entry had occurred at the time of the trade’s exit.
  2. Risk Assessment: Regression analysis is also instrumental in predicting trades at risk of hitting stop loss. It considers various data points, including market volatility, trade volume, and historical performance, to gauge the likelihood of stop loss triggers.

k-Means Clustering:

In addition to regression analysis, the Entropy Alpha Strategy employs k-means clustering as part of its Machine Learning arsenal.

  1. Cluster-Based Insights: K-means clustering is used to segment trade data into distinct clusters based on similar characteristics. This clustering process enhances the model’s ability to categorize trades effectively and identify patterns within the data.
  2. Trade Profiling: By clustering trades with similar attributes, the model can profile trades with shared characteristics. This aids in recognizing specific trade scenarios and making data-driven predictions about entry timing.

The Synergy of Regression Analysis and k-Means Clustering:

These two Machine Learning techniques work in tandem within the Entropy Alpha Strategy:

  • Regression analysis refines trade entries based on historical data and relationships between variables, optimizing profitability and risk management.
  • K-means clustering aids in categorizing and profiling trades, enhancing the model’s ability to identify patterns and similarities among trades.
Post a comment

Leave a Comment

Your email address will not be published. Required fields are marked *