Perbandingan Model Long Short-Term Memory dan Bidirectional Long Short-Term Memory dalam Memprediksi IHSG Berdasarkan Faktor Indeks Global

Majid, Muhammad Althaf (2024) Perbandingan Model Long Short-Term Memory dan Bidirectional Long Short-Term Memory dalam Memprediksi IHSG Berdasarkan Faktor Indeks Global. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5006201069-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2026. Download (3MB) | Request a copy

Abstract

Investasi di pasar modal merupakan salah satu kegiatan yang popular yang dilakukan masyarakat, khususnya Indonesia. Hal ini didukung dengan jumlah investor yang terus meningkat setiap tahunnya. Saham merupakan instrumen investasi yang memiliki tingkat risiko yang besar karena mampu memberikan return yang lebih besar dibandingkan instrumen lain. Investor harus mampu menganalisis dan memahami bagaimana cara memilih saham yang tepat sebagai tempat berinvestasi sehingga return yang diharapkan di masa depan dapat terwujud. IHSG merupakan indeks harga saham di Bursa Efek Indonesia (BEI) yang digunakan sebagai indikator untuk mencerminkan kinerja saham-saham perusahaan melalui pergerakan harga saham. Karenanya, IHSG menjadi acuan para investor dalam berinvestasi. Bursa efek yang tergolong maju secara umum mampu menggambarkan dampaknya terhadap bursa lainnya. Beberapa penelitian telah membuktikan adanya dampak indeks global satu dengan lainnya. Indeks global adalah istilah yang mengacu pada indeks masing-masing negara untuk mewakili pergerakan kinerja saham negaranya. Peramalan dapat menjadi salah satu analisis yang membantu para investor dalam mengambil keputusan bijak ketika berinvestasi. Pada umumnya, peramalan IHSG banyak dilakukan dengan menggunakan berbagai metode termasuk Long Short-Term Memory (LSTM) dan Bidirectional Long Short Term Memory (Bi-LSTM) Untuk memperoleh model peramalan IHSG, dibutuhkan metode yang sesuai dan cocok terutama untuk data yang memiliki jumlah besar. LSTM merupakan pengembangan Recurrent Neural Network (RNN) yang memiliki kemmapuan untuk mengingat informasi dalam jangka waktu yang lebih panjang, sedangkan Bi-LSTM merupakan pengembangan dari LSTM yang memiliki kemampuan untuk mengingat informasi lebih panjang dan dapat memahami pola yang lebih kompleks dibandingkan LSTM. Dalam penelitian ini, dilakukan peramalkan IHSG berdasarkan faktor indeks global periode 1 Januari 2018 – 30 Juni 2023 menggunakan metode LSTM dan Bi-LSTM. Hasil penelitian menunjukkan bahwa model terbaik Bi-LSTM (6-9-1) memiliki performa yang lebih baik dalam memprediksi dan meramalkan pergerakan IHSG dengan nilai MAPE sebesar 0,572314% lebih baik dibandingkan model terbaik LSTM (4-10-1) yang memiliki MAPE sebesar 0,74326%. Dengan adanya peramalan berdasarkan model Bi-LSTM ini, diharapkan dapat membantu investor dalam pengambilan keputusan di Bursa Efek Indoensia (BEI).
=================================================================================================================================
Investing in the capital market is one of a popular activities carried out by the public, especially in Indonesia. This is supported by the increasing number of investors each year. Stocks are investment instruments that come with a high level of risk but have the potential to provide greater returns compared to other instruments. Investors must be able to analyze and understand how to choose the right stock as a place to invest so that the expected return in the future can be realized. This requires strong analytical skills, and investors must make wise investment decisions based on their personal analysis of the relevant companies. The IHSG (Indonesia Stock Exchange Composite Index) is a stock price index in the Indonesia Stock Exchange (BEI) that serves as an indicator reflecting the performance of company stocks through stock price movements. Therefore, IHSG becomes a reference for investors in making investment decisions. Advanced stock exchanges generally have a strong influence on other stock exchanges. Several studies have proven the influence of one global index on another. Global index is a term that refers to each country's index to represent the movement of its country's stock performance. Forecasting IHSG can be one of the analyses that help investors make wise decisions when investing. Typically, IHSG forecasting is done using methods such as Auto-Regressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Support Vector Machine (SVM). To obtain an IHSG forecasting model, an appropriate and suitable method is needed, especially for data that has a large amount. LSTM is a development of Recurrent Neural Network (RNN) which has the ability to remember information in a longer period of time, while Bi-LSTM is a development of LSTM which has the ability to remember information longer and can understand more complex patterns than LSTM.. This final project research will forecast IHSG based on global index factors for the period from January 1, 2018, to June 31, 2023, using the LSTM and bi-LSTM methods. The results showed that the best Bi-LSTM model (6-9-1) had a better performance in predicting and forecasting JCI movements with a MAPE value of 0.572314% better than the best LSTM model (4-10-1) which had a MAPE of 0.74326%. With forecasting based on the Bi-LSTM model, it is expected to help investors in making decisions on the Indonesia Stock Exchange (IDX).

Item Type:	Thesis (Other)
Uncontrolled Keywords:	bi-LSTM, IHSG, Global Index, Indeks Global, LSTM, Mean Absolute Percentage Error
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > Q Science (General) > Q325.78 Back propagation Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User:	Muhammad Althaf Majid
Date Deposited:	31 Jan 2024 06:06
Last Modified:	31 Jan 2024 06:06
URI:	http://repository.its.ac.id/id/eprint/105784

Actions (login required)

View Item