Neural Network Backpropagation Identification of Jakarta Islamic Index (JII) Stock Price Patterns

Neural Network Backpropagation Identifikasi Pola Harga Saham Jakarta Islamic Index (JII)

  • Musli Yanto UPI YPTK Padang
  • Liga Mayola University Putra Indonesia YPTK Padang
  • M. Hafizh
Keywords: JST, Backpropagation, Knowladge, Pattern , and Jakarta Islamic Index (JII) Pattern and Stock Price IndexJST, Backpropagation, Knowladge, Pattern , and Jakarta Islamic Index (JII) Pattern and Stock Price Index

Abstract

Jakarta Islamic Index (JII) is an organization engaged in the economy with the aim to pay attention to stock movements every day. With the JII, people who do not understand about shares and their movements, will be easy to know and understand the movement of shares that occur at certain times. The problem in this research is that many investors are unable to predict the rise and fall of stock prices. The prediction process can be done with a backpropagation algorithm. The algorithm is a concept of computer science which is widely used in the case of analysis, prediction and pattern determination. The process starts from the analysis of the variables used namely interest rates, exchange rates, inflation rates and stock prices that occurred in the previous period. The variables used are continued in the formation of network patterns and continued in the process of training and testing in order to produce the best network patterns so that they are used as a process of identifying JII stock price movements. The results obtained in the form of the value of stock price movements with an error rate based on the MSE value of 11.85% so that this study provides information in the form of knowledge for making a decision. The purpose of the research is used as input for investors in identifying share prices. In the end, the benefits felt from the results of this study, investors can make an initial estimate before investing in JII.

Downloads

Download data is not yet available.

References

Liga Mayola, Sigit Sanjaya, Wifra Safitri, 2018, Identifikasi Karakteristik Jakarta Islamic Index Dengan Menggunakan Algoritma K-Means, Jurnal Sebatik No. 22, Vol. 2

Eka Ajeng Dian Anggraini, 2018, Determinan Return Saham: Jakarta Islamic Index Vs Lq 45, Jurnal Keuangan dan Perbankan Syariah Volume 6 , No. 2.

Lawrence, Ramon, 2018, Using Neural Networks To Forecast Stock Market Prices, University of British Columbia.

Songa, Yue-Gang Zhoub, Yu-Long, Hanc, Ren-Jie, 2018, Neural networks for stock price prediction, Journal of Difference Equations and Applications Vol. 00, No. 00

Eko Riyanto, 2017, Peramalan Harga Saham Menggunakan Jaringan Saraf Tiruan Secara Supervised Learning Dengan Algoritma Backpropagation, Jurnal Informatika Upgris Vol. 3, No. 2

Nazla Nurmila, Aris Sugiharto, Eko Adi Sarwoko,2006, Algoritma Back Propagation Neural Network Untuk Pengenalan Pola Karakter Huruf Jawa, Jurnal Masyarakat Informatika, Vol: 1, No: 1

Rini Sovia, Musli Yanto, Widya Nursanty, 2016, Implementation Of Signature Recognition By Using Backpropagation, UPI YPTK Journal of Computer Science and Information Technology.

Fauzi, Rahmad, “Implementasi Jaringan Saraf Tiruan Dengan Metode Backpropagation Terhadap Bibit Tanaman Karet”, ISSN : 2527-4295 Vol.1 No.1 Edisi Mei 2016 Jurnal Education and development STKIP Tapanuli Selatan.

Artanti, Indra setianigsih dan Ika Damayanti, 2016, “Aplikasi Metode Jaringan Saraf Tiruan Untuk Memprediksi Data Indeks Harga Saham Gabungan Di Indonesia”, Statistika, Vol. 4, No. 2

Mira, Faula Arina, Ratna Ekawati, 2009, “Peramalan Jumlah Permintaan Produksi Menggunakan Metode Jaringan Syaraf Tiruan (JST) Backpropagation” Jurnal Teknik Industri, Vol.1, No.2, Juni 2013, pp.174-179 ISSN 2302-4951.

Siang, Jong Jek. 2005. Jaringan Saraf Tiruan dan Pemrogramannya Menggunakan MATLAB, Yogyakarta: Penerbit Andi.

Fernandya, Riski Hartantri Dan Ardi Pujiyanta, 2014, “Deteksi Penyakit Dan Serangan HamaTanaman Buah Salak Menggunakan Jaringan Saraf Tiruan (JST) Dengan Metode Perceptron”, Urnal Sarjana Teknik Informatika E-Issn: 2338-5197 Volume 2 Nomor 2.

Magdalena Erniati, Beni Irawan Dan Dwi Marisa Midyanti, 2016, “Prediksi Penyakit Tht (Telinga, Hidung, Tenggorokan) Dengan Metode Jaringan Saraf Tiruan Perceptron”, Sistem Komputer Untan Issn : 2338-493x, Volume 4, No. 2 (2016), Hal. 56-65.

Afriyanti, L. 2010. Rancang Bangun Tool Untuk Jaringan Saraf Tiruan (JST) Model Perceptron. Makalah disajikan dalam Seminar Nasional Aplikasi Teknologi Informasi, Yogyakarta, 19Juni 2010.

M.J. Islam, Q. M.J. Wu, M. Ahmadi, M.A. Sid-Ahmed, 2009. Neural Network Based Handwritten Digits Recognition- An Experiment and Analysis. University of Windsor, Canada.

Published
2020-02-08
Section
Artikel Teknologi Informasi