Staged Optimization of a Neural-Network Trading EA

Summary

This document describes an Expert Advisor built around a simple neural network and two indicators: Laguerre_PlusDi and SilverTrend_Signal. Its setup relies on three sequential optimization passes, each activated by setting a Pass parameter and optimizing a different subset of inputs. After the third pass, the EA is left configured with Pass set to 3 and the final pass’s selected parameters enabled.

The only stated testing detail is that all optimization stages use the one-minute OHLC mode. The document gives no performance results, market or instrument scope, validation procedure, or risk controls. It therefore explains an optimization workflow rather than establishing that the EA is profitable or robust; the prescribed staged tuning may also be sensitive to the data and settings used.

Key ideas

• The EA combines a simple neural network with Laguerre_PlusDi and SilverTrend_Signal indicators.
• Optimization proceeds through three passes, with a different group of parameters selected at each stage.
• All optimization stages are specified to use one-minute OHLC data mode.
• The document provides no performance evidence or out-of-sample validation details.

Tags

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