UJI PERFORMA PREDIKSI METODE AUTO REGRESSIVE FRACTIONALLY INTEGRATED MOVING AVERAGES DAN LONG SHORT-TERM MEMORY DENGAN DATA SAHAM DUA PERUSAHAAN BANK

Berli Suharmanto, . (2023) UJI PERFORMA PREDIKSI METODE AUTO REGRESSIVE FRACTIONALLY INTEGRATED MOVING AVERAGES DAN LONG SHORT-TERM MEMORY DENGAN DATA SAHAM DUA PERUSAHAAN BANK. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (9kB)
[img] Text
AWAL.pdf
Download (328kB)
[img] Text
BAB 1.pdf
Download (61kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (528kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (212kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (2MB)
[img] Text
BAB 5.pdf
Download (50kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (199kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (78kB)
[img] Text
LAMPIRAN.pdf
Restricted to Repository UPNVJ Only
Download (1MB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (18MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (318kB)

Abstract

Stocks are one way for people to invest for the long term. Stock data can be used for analysis in a study using an algorithm to obtain predictive value information that can be used in the future. In this study the algorithm used to obtain the prediction model is the Auto Regressive Fractionally Integrated Moving Averages (ARFIMA) and Long Short-Term Memory (LSTM) methods. The stock data used is stock data from IDX with Bank Raya Indonesia Tbk stock data. and Bank IBK Indonesia Tbk. in the period September 2019 to December 2022 with Closing data as a feature. The processing results of the best ARFIMA model are the ARFIMA(8,0.5,0) model from BRI data with SMAPE of 5.57% and the ARFIMA model(4,0.5,0) from Bank IBK Indonesia data with SMAPE of 23.31%. For the best results, BRI's LSTM is 1.61% with 150 epochs and Bank IBK Indonesia's LSTM is 2.22% with 300 epochs. The best model produced is the LSTM model with 150 epochs for BRI and the LSTM model with 300 epochs.

Item Type: Thesis (Skripsi)
Additional Information: [No.Panggil: 1910511033] [Pembimbing: Iin Ernawati] [Penguji 1: Jayanta] [Penguji 2: Catur Nugrahaeni]
Uncontrolled Keywords: Stock, Forecasting, ARFIMA, LSTM, Prediction
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User: Berli Suharmanto
Date Deposited: 17 Jul 2023 08:31
Last Modified: 27 Jul 2023 04:51
URI: http://repository.upnvj.ac.id/id/eprint/25087

Actions (login required)

View Item View Item