Artificial Neural Network Model for prediction of time-series data is revisited on analysis of the Indonesian stock-exchange data. We introduce the use of Multi-Layer Perceptron to percept the modified Poincare-map of the given financial time-series data. The modified Poincare-map is believed to become the pattern of the data that transforms the data in time-t versus the data in time-t+1 graphically. We built the Multi-Layer Perceptron to percept and demonstrate predicting the data on specific stock-exchange in Indonesia.Keywords: neural network, multi-layer perceptron, Poincare map, prediction, financial timeseries data There has been a lot of works on forecasting and prediction of the future value using neural network perception, e.g.: the previous paper, Situngkir & Surya (2003) that explained how to utilize multi-layer perceptron in predicting time series data. We actually can obtain, using this analysis, sufficiently good prediction of two up to three steps of time forward. It should be admitted that for the sake of prediction, the very wish of a predictor is to predict time series data in a wide length and as precise as possible. We also show that basically prediction analysis done was a top-down prediction analysis, means viewing a problem from such time series data, without concerning aspects caused the time series data.Poincare map is simply a map that showing a pattern from its time series data. Poincare map is a map that is not time series map, yet it allows transversal changes of time series data in each time of iteration; in this way each element of data displayed can no longer be viewed differently from time series that represent them. In fact, every time series data has been inherent with the data that graphically represented. It should be admitted that Poincare map has been rarely used in social analysis. Traditional approaches identifying chaos (such as Lyapunov, correlation dimension and or spectral analysis) are rarely used in analyzing social system. This is factual since those ways are not sensitive to the poor amount of data (Marion, et al., 1997). We know that in the social system, data gained, are usually few, except financial time seriessomething that we would study further in the rest of this paper.
The paper revisits the investment simulation based on strategies exhibited by Generalized (m, 2)-Zipf law to present an interesting characterization of the wildness in financial time series. The investigations of dominant strategies on each specific time series shows that longer words dominant in larger time scale exhibit shorter dominant ones in smaller time scale and vice versa. Moreover, denoting the term wildness based on persistence over short term trend and memory represented by particular length of words, we can see how wild historical fluctuations over time series data coped with the Zipf strategies.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.