Using Bollinger Band Width as a Neural Network Input

Summary

The document describes an Expert Advisor that uses recent Bollinger Band Width values in a neural network method. Band Width is presented as the percentage spread between the upper and lower Bollinger Bands, normalized by the middle band in the implementation described. Narrowing bands indicate lower measured volatility, while widening bands indicate rising volatility. The system takes a recent sequence of width readings, scales the inputs, and applies a neural network formula; the document points readers toward an external article for implementation details.

A test is reported for a period from January to April 2013, with an initial deposit of 10,000 and gross profit of 36,000 over three and a half months. These figures are the author's reported test results, with no full performance report or validation details in the text. The author advises against using the system in a real account and suggests that volume indicators could be combined with it. The description does not specify the neural network design, trading rules, risk controls, or whether the reported result accounts for costs or out-of-sample testing.

Key ideas

• Bollinger Band Width measures the spread between the upper and lower bands relative to the middle band.
• Lower Band Width corresponds to lower measured volatility, while rising width corresponds to increasing volatility.
• The Expert Advisor feeds recent Band Width readings into a neural network method after scaling them.
• The document reports a short historical test but gives no detailed validation or cost analysis.
• The author cautions against using the system in a live account.

Tags

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