Combining a Two-Layer Neural Network with MACD Signals

Summary

This document describes an automated trading system framework that combines a two-layer neural network with MACD when assessing whether to open positions. The neural network and indicator signals are analyzed together; MACD is not merely a fallback used only when the network gives a neutral reading.

The author presents the system as a starting structure that can be extended with other indicators or groups of indicators and additional optimization. The text points readers to a separate MTC Combo page for details on applying and training the network. It offers an author opinion that hourly charts and major currency pairs give the best results, but supplies no backtest figures, evaluation method, or evidence supporting that view. The recommendation should therefore be treated as an unverified suggestion rather than a demonstrated performance claim.

Key ideas

• The framework combines neural-network output and MACD in assessing trade entries.
• Indicator signals are considered alongside network signals rather than only when the network is neutral.
• The indicator component can be replaced or extended, and the system can be optimized.
• The suggested hourly timeframe and major currency pairs are an author opinion without supporting results in the document.

Tags

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