Introduction to artificial neural systems
Introduction to artificial neural systems
Computational learning techniques for intraday FX trading using popular technical indicators
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
This paper proposes an Artificial Neural Networks (ANN) model which feeds on inputs from popular technical indicators to predict trading signals, which is expected to be useful for active intra-day traders. The data used to build the model is the high frequency data of intra-day stocks from some industry sectors in the Indonesia Stock Exchange market. The technical indicators used as the inputs are the Price Channel Indicator, the Adaptive Moving Averages, the Relative Strength Index, the Stochastic Oscillator, the Moving Average Convergence-Divergence, the Moving Averages Crossovers and the Commodity Channel Index. The network architecture used in this paper is the multi layer feedforward perceptron with one hidden layer and trained using the backpropagation method. The performance of the model will be compared to a naïve buy-and-hold strategy and a maximum profit profile. The result of our experiments showed that the model performs better than the naïve strategy. Therefore, it can be concluded that the ANN is a useful method to generate trading signal predictors for intra-day traders from the high frequency data.