Neural network revisited: perception on modified Poincare map of financial time-series data

Abstract

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.

Application of Artificial Intelligence in Stock Market Forecasting: A Critique, Review, and Research Agenda

“…Even though most of the studies have analyzed stocks from developed countries, equity stock markets from emerging nations are also considered in some works. From Asia, these include: the Korean stock market (Baek and Kim 2018;Oh and Kim 2002); the Chinese stock market (Baek and Kim 2018;Cao et al 2011;Chen et al 2018;Oh and Kim 2002); the Indian stock market (Bisoi and Dash 2014;Mehta et al 2021); the Malaysian stock market (Sagir and Sathasivan 2017); the Thailand stock market (Inthachot et al 2016); the Taiwan stock market (Hao et al 2021;Wei and Cheng 2012); the Philippines stock market ; the Indonesian stock market (Situngkir and Surya 2004); and the Bangladesh stock market (Mahmud and Meesad 2016). From Latin America, this includes the Brazilian stock market (De Oliveira et al 2013;De Souza et al 2012).…”

Indonesia Embraces the Data Science

“…√∑ ( ) 2 √∑ ( ) 2 (7) based upon the sentiment of actor and actor to a public topic , writen as and respectively. From this modeling, we have the sentiment-mapping of Indonesian celebrities, summarized from their statements as recorded by journalism [21]. As demonstrated in figure 6, the Sentiment Mapping from the Newsmedia Processing Suite made it possible to see the clustered celebrities based on some issues being highly reported by the news channels.…”

“…Statements conveyed in Indonesian language, 𝜔𝜖𝕃, is transormed into sentiment between one actor to another, be it positive sentiment (when two actors agree with one or more issues), negative (conflicting opinion), or neutral, (7) based upon the sentiment of actor 𝑖 and actor 𝑗 to a public topic 𝑘, writen as 𝑣 𝑖𝑘 and 𝑣 𝑗𝑘 respectively. From this modeling, we have the sentiment-mapping of Indonesian celebrities, summarized from their statements as recorded by journalism [21]. As demonstrated in figure 6, the Sentiment Mapping from the Newsmedia Processing Suite made it possible to see the clustered celebrities based on some issues being highly reported by the news channels.…”

Towards Complexity Studies of Indonesian Songs

“…Gündüz & Gündüz [4] shows that we can see the internal structure of the song by starting our observation from here. A previous work on time series data has also incorporated this kind of method [9]. scattering along the diagonal axis of the trend line: the smaller it is, the more compact the melodic structure is.…”