Analisis Prediksi Harga Saham Perusahaan Nikel Untuk Baterai Kendaraan Listrik Dengan Metode Arima Box Jenkins Dan Neural Network Autoregression

Utomo, Ardy (2025) Analisis Prediksi Harga Saham Perusahaan Nikel Untuk Baterai Kendaraan Listrik Dengan Metode Arima Box Jenkins Dan Neural Network Autoregression. Masters thesis, Institut Teknologi Sepuluh Nopember.

Text 6032221199-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 April 2027. Download (4MB) | Request a copy

Abstract

Pemerintah Indonesia terus mendorong pengembangan Kendaraan Bermotor Listrik Berbasis Baterai (KBLBB), di mana nikel merupakan komponen utama dalam baterai kendaraan listrik. Peningkatan permintaan nikel memberikan sentimen positif terhadap harga saham emiten nikel seperti PT Aneka Tambang (ANTM), PT Vale Indonesia (INCO), PT Merdeka Battery Materials (MBMA), dan PT Trimegah Bangun Persada (NCKL). Penelitian ini bertujuan untuk meramalkan harga saham emiten-emiten tersebut menggunakan metode Auto Regressive Integrated Moving Average (ARIMA) dan Neural Network Autoregression (NAR) dengan data historis periode 1 Juli 2023 hingga 31 Oktober 2024. Model ARIMA diidentifikasi melalui uji stasioneritas, analisis fungsi autokorelasi (ACF) dan autokorelasi parsial (PACF), serta estimasi parameter dan diagnostik residual. Hasil model ARIMA digunakan sebagai input dalam Jaringan Syaraf Tiruan (JST) untuk membentuk prediksi NAR. Hasil penelitian menunjukkan bahwa model ARIMA memberikan performa terbaik pada saham NCKL (MAPE 1,88%) namun kurang stabil pada data testing. Sebaliknya, model NAR lebih unggul dalam menangkap pola non-linear dengan performa terbaik pada saham NCKL (NAR(2), MAPE 1,42%) dan ANTM (NAR(2), MAPE 1,61%). Secara keseluruhan, model NAR memberikan hasil prediksi yang lebih akurat dan stabil dibandingkan ARIMA. Hasil ini dapat digunakan sebagai alat bantu efektif dalam pengambilan keputusan investasi, pengelolaan portofolio, dan pengembangan strategi investasi di sektor nikel berbasis data historis.
================================================================================================================================
The Indonesian government continues to promote the development of Battery Electric Vehicles (BEVs), where nickel plays a critical role as a primary component in electric vehicle batteries. The increasing demand for nickel has positively impacted the stock prices of major nickel companies, such as PT Aneka Tambang (ANTM), PT Vale Indonesia (INCO), PT Merdeka Battery Materials (MBMA), and PT Trimegah Bangun Persada (NCKL). This study aims to forecast the stock prices of these companies using the Auto Regressive Integrated Moving Average (ARIMA) and Neural Network Autoregression (NAR) methods, utilizing historical stock price data from July 1, 2023, to October 31, 2024. The ARIMA model was identified through stationarity tests, autocorrelation function (ACF), and partial autocorrelation function (PACF) analysis, followed by parameter estimation and residual diagnostics. The results of the ARIMA model were then used as input for the Neural Network Autoregression (NAR) system to improve predictive performance. The findings show that the ARIMA model performed best on NCKL stock (MAPE 1.88%) but exhibited instability when applied to testing data. Conversely, the NAR model outperformed ARIMA in capturing non-linear patterns, with the best performance achieved on NCKL (NAR(2), MAPE 1.42%) and ANTM (NAR(2), MAPE 1.61%). Overall, the NAR model provided more accurate and stable predictions compared to ARIMA. These predictive models can serve as effective tools for investment decision-making, portfolio management, and the development of data-driven investment strategies in the nickel sector.

Item Type:	Thesis (Masters)
Uncontrolled Keywords:	ARIMA, Baterai Kendaraan Listrik, Battery Electric Vehicles, Neural Network Autoregression, Nikel, Nickel, Prediksi Harga Saham, Stock Price Prediction.
Subjects:	T Technology > T Technology (General) > T174 Technological forecasting
Divisions:	Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User:	Ardy Utomo
Date Deposited:	03 Feb 2025 01:06
Last Modified:	03 Feb 2025 01:06
URI:	http://repository.its.ac.id/id/eprint/117844

Actions (login required)

View Item