Combining robust Dynamic Neural Networks with traditional technical indicators for generating mechanic trading signals

Forecasting assets’ prices is the aim of each trader, although the trading approaches employed may vary a lot. The development of machine learning techniques has brought the opportunity to design mechanic trading systems based on dynamic artificial neural networks. The aim of this paper is to combine traditional technical indicators [such as exponential weighted moving average (EWMA), percentage volume oscillator (PVO) and stochastic indicator — %K and %D] with the nonlinear autoregressive networks (NAR and NARX). The first part of the paper describes how neural networks designed for forecasting time series work, the second one performs a deeper validation of the code and the third one combines the dynamic networks with traditional technical indicators in order to generate reliable mechanic signals. The article ends with a back testing of the trading system performed on Dow Jones Industrial Average and on Nasdaq Composite Indexes.