Analisis prediktif harga saham dengan menggunakan metode arima dan arima-lstm = Predictive analysis of stock prices using arima and arima-lstm methods

Tauhalomoan, Patrick Mangara (2024) Analisis prediktif harga saham dengan menggunakan metode arima dan arima-lstm = Predictive analysis of stock prices using arima and arima-lstm methods. Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (217kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (732kB)
[thumbnail of ToC] Text (ToC)
ToC.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (793kB)
[thumbnail of Chapter1] Text (Chapter1)
Chapter1.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (2MB)
[thumbnail of Chapter2] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter3] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter4] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (10MB)
[thumbnail of Chapter5] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (709kB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (710kB)
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (5MB)

Abstract

Pergerakan harga saham dalam prakteknya cenderung memiliki pergerakan yang acak. Hal ini membuat para investor kesulitan dalam membuat sebuah keputusan investasi. Oleh sebab itu, peramalan harga saham akan menjadi alat bantu ataupun referensi para investor dalam membuat keputusan investasi. Peramalan harga saham dapat dibuat dengan beragam metode seperti model deret waktu, kecerdasan buatan seperti artificial neural network, regresi, dan beragam metode lainnya. Dalam meramalkan harga saham tersebut, penelitian ini akan menggunakan dua metode, yaitu ARIMA dan hybrid ARIMA-LSTM dalam memprediksi harga saham harian di Indonesia. Penelitian ini akan melakukan pemodelan ARIMA dan ARIMA-LSTM, untuk kemudian dilakukan prediksi terhadap harga saham harian di Indonesia melalui kedua metode tersebut. Saham harian yang diteliti merupakan periode Januari 2014 sampai dengan Desember 2023. Setelah hasil prediksi dari kedua metode diperoleh, maka akan dilakukan perbandingan untuk mengetahui metode yang terbaik. Pada penelitian ini, diperoleh hasil bahwa lima dari enam saham yang diprediksi membuktikan bahwa metode ARIMA-LSTM lebih unggul dalam memprediksi harga saham harian di Indonesia. Hal ini dapat dilihat dari nilai MSE, RMSE, dan MAPE yang dihasilkan pada kedua model. / The movement of stock prices in practice tends to exhibit random fluctuations, making it difficult for investors to make investment decisions. Therefore, stock price forecasting serves as a tool or reference for investors in making investment decisions. Stock price forecasting can be carried out using various methods such as time series models, artificial intelligence techniques like artificial neural networks, regression, and various other methods. In this research, two methods, namely ARIMA and hybrid ARIMA-LSTM, are employed to predict daily stock prices in Indonesia. The study involves modeling ARIMA and ARIMA-LSTM, followed by predictions of daily stock prices in Indonesia using both methods. The daily stock data under investigation are from January 2014 to December 2023. After obtaining the prediction results from both methods, a comparison is conducted to determine the superior method. The study reveals that five out of six stocks predicted demonstrate the superiority of the ARIMA-LSTM method in predicting daily stock prices in Indonesia. This thing can be seen from the values of MSE, RMSE, and MAPE generated by both models.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Tauhalomoan, Patrick Mangara
NIM01112200027
patrick.nainggolan7@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Margaretha, Helena
NIDN0312057504
helena.margaretha@uph.edu
Thesis advisor
Widjaja, Petrus
NIDN0314095901
petrus.widjaja@uph.edu
Uncontrolled Keywords: autoregressive integrated moving average (ARIMA); long short-term memory (LSTM); peramalan; harga saham; autoregressive integrated moving average (ARIMA); long short-term memory (LSTM); prediction; stock price.
Subjects: Q Science > QA Mathematics
Divisions: University Subject > Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Current > Faculty/School - UPH Karawaci > Faculty of Science and Technology > Mathematics
Depositing User: Patrick Mangara Tauhalomoan
Date Deposited: 23 Jul 2024 01:17
Last Modified: 23 Jul 2024 01:17
URI: http://repository.uph.edu/id/eprint/64220

Actions (login required)

View Item
View Item