Record Details

TEKNIK JARINGAN SYARAF TIRUAN FEEDFORWARD UNTUK PREDIKSI HARGA SAHAM PADA PASAR MODAL INDONESIA

Jurnal Informatika

View Archive Info
 
 
Field Value
 
Title TEKNIK JARINGAN SYARAF TIRUAN FEEDFORWARD UNTUK PREDIKSI HARGA SAHAM PADA PASAR MODAL INDONESIA
 
Creator Bambang DP., Budi; Program Pascasarjana Teknik Kendali, Institut Teknologi Bandung (ITB)
J. Widodo, Rochani; Program Pascasarjana Teknik Kendali, Institut Teknologi Bandung (ITB)
Z. Sutalaksana, Iftikar; Program Pascasarjana Teknik Kendali, Institut Teknologi Bandung (ITB)
L. Singgih, Moses; Program Pascasarjana Teknik Kendali, Institut Teknologi Bandung (ITB)
 
Subject stock market prediction, time series feedforward neural networks
 
Description To predict the condition of stock price, several technical analysis models have been used and expanded such as MACD, Fourier Transform, Accumulator Swing Index , Stochastic Oscillator etc. For input they are using the various prices such as Open, high, low , close , volume, BID, ASK price, and the output is a graphic that shows the decision whether to sell, buy or hold. Another method to determine the stock price by using Fundamental Analysis method. Fundamental method is an analysis that is based on the ratio or financial report from the existing company.
Neural Network System Technology has been implemented in various applications especially in introduce the pattern. This power has attracted several people to use Neural Network for medical, Finance, Investment and marketing. Assuming that the prediction of the output system (next output prediction) is deterministic, than the suitable N.N model to predict it is Feed Forward.
The prediction of the stock price is the complex interaction between unstable market and unknown random processes factor. The data from stock price can be determined by time series. If we have daily data from a certain period, for example : Xt(t = 1,2,...) than the stock price for the next period (t+h) can be predicted (the timing used can be in hourly, daily, weekly, monthly or yearly). To get the good prediction, the inputs from several aspects of the share prices have to be input in Neural Network after that the weighing principal can be adapted to minimize the wrong prediction in the first future steps. By using the final weighing, an action is done to done to minimize the total error in the second future steps. Due to that, the risk of Investor's decision to sell or buy the stock can be minimized. This paper will discuss on how to use and implement Time Series Neural Network to predict the stock market in Semen Gresik (SMGR) and Gudang Garam (GGRM)


Abstract in Bahasa Indonesia :

Dalam memprediksi suatu kondisi harga saham, beberapa model analisa teknik telah dipakai dan dikembangkan, beberapa analisa tersebut seperti : MACD , Fourier Transform, Accumulator Swing Index, Stochastic Oscilator dan lain lain. Sebagai masukannya digunakan beberapa macam kombinasi harga seperti : harga pembukaan, tertinggi, terendah, penutupan kemarin dan penutupan hari ini serta volume perdagangan. Dan sebagai keluaran adalah suatu grafik yang menampilkan suatu keputusan beli atau jual. Suatu cara lain dalam menentukan harga saham adalah dengan menggunakan metoda 'Fundamental Analysis', yaitu suatu analisa dimana penampilan dari suatu kinerja perusahaan didasarkan atas ratio-ratio / laporan keuangan yang ada.
Teknologi sistem jaringan syaraf tiruan telah di-implementasikan dalam berbagai aplikasi terutama dalam hal pengenalan pola. Kemampuan inilah yang telah menarik beberapa kalangan dalam menggunakan jaringan syaraf tiruan untuk keperluan kesehatan, keuangan , investasi, marketing dan lain lain. Pada makalah ini akan dibahas penggunaan Jaringan syaraf tiruan Feedforward/Backpropagarion.
Data dari harga saham dapat diperlakukan secara 'time series' . Jika kita mempunyai data harian selama perioda tertentu, misal : Xt (t=1,2,......), maka harga saham pada perioda berikutnya (t+h) dapat diprediksi (waktu yang digunakan bisa jam, harian, mingguan , bulanan ataupun tahunan) . Demikian seterusnya dilakukan suatu iterasi berulang hingan N hari kerja. Untuk mendapatkan hasil prediksi yang baik maka pada jaringan syaraf buatan hasus di-umpankan suatu masukan yang mewakili dari beberapa aspek atau segi penunjang harga suatu saham. Kemudian dilakukan prinsip pembobotan yang diadaptasikan untuk meminimumkan kesalahan prediksi pada satu langkah kedepan. Dengan menggunakan bobot akhir dilakukan suatu tindakan untuk meminimumkan kesalahan total untuk iterasi berikutnya. Saham yang akan dibahas adalah saham Semen Gresik (SMGR) dan Gudang Garam (GGRM)


Kata kunci: prediksi harga saham, jaringan syaraf tiruan, time series feedforward neural networks
 
Publisher Institute of Research and Community Outreach - Petra Christian University
 
Date 2004-06-18
 
Type info:eu-repo/semantics/article
info:eu-repo/semantics/publishedVersion
 
Format application/pdf
 
Identifier http://jurnalinformatika.petra.ac.id/index.php/inf/article/view/15793
10.9744/informatika.1.1.pp. 33-37
 
Source Jurnal Informatika; Vol 1, No 1 (1999): MAY 1999; pp. 33-37
 
Language eng
 
Relation http://jurnalinformatika.petra.ac.id/index.php/inf/article/view/15793/15785
 
Rights Authors who publish with this journal agree to the following terms:Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).