A Single-Layer Perceptron Expert Advisor for Quote Direction

Summary

The document describes an Expert Advisor that uses a single-layer neural network, identified as a perceptron, to classify the direction of quote movement. The implementation draws on the iAC indicator and bar opening-time history. It also reports a testing setup on a 30-minute chart, with a specified initial deposit and historical period, and distinguishes optimization using one-minute OHLC data from a single test using real ticks.

This is a brief description of a machine-learning trading program and its evaluation configuration, rather than a full account of its signal design. It does not provide the optimization parameter ranges, trade rules, performance statistics, or evidence of out-of-sample robustness. The different data modes used for optimization and testing may also make direct comparisons difficult. The excerpt therefore supports understanding the broad model and testing setup, but not judging whether the Expert Advisor is profitable or generalizes well.

Key ideas

• The Expert Advisor uses a single-layer perceptron to classify quote direction.
• Its inputs include the iAC indicator and opening-time information for historical bars.
• The described configuration uses a 30-minute chart and a historical test period.
• Optimization and the single reported test use different price-data simulation modes.
• The excerpt contains no performance statistics or detail sufficient to assess robustness.

Tags

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