IKHSAN, MUHAMMAD (2025) PREDIKSI HARGA SAHAM PT BUKIT ASAM (PTBA) DENGAN METODE LONG SHORT-TERM MEMORY (LSTM). S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 Cover.pdf Download (262kB) | Preview |
|
![]() |
Text (BAB I)
02 Bab 1.pdf Restricted to Registered users only Download (31kB) |
|
![]() |
Text (BAB II)
03 Bab 2.pdf Restricted to Registered users only Download (125kB) |
|
![]() |
Text (BAB III)
04 Bab 3.pdf Restricted to Registered users only Download (44kB) |
|
![]() |
Text (BAB IV)
05 Bab 4.pdf Restricted to Registered users only Download (121kB) |
|
![]() |
Text (BAB V)
06 Bab 5.pdf Restricted to Registered users only Download (24kB) |
|
![]() |
Text (DAFTAR PUSTAKA)
07 Daftar Pustaka.pdf Restricted to Registered users only Download (144kB) |
|
![]() |
Text (LAMPIRAN)
08 Lampiran.pdf Restricted to Registered users only Download (200kB) |
Abstract
High stock price fluctuations in the mining sector pose a challenge for investors in their decisionmaking process. This research aims to develop and evaluate a stock price prediction model for PT Bukit Asam Tbk (PTBA) using the Long Short-Term Memory (LSTM) method. The data utilized is the historical daily closing price of PTBA from January 1, 2014, to December 31, 2023, which is divided into 80% training data and 20% testing data. Experiments were conducted by testing 16 different hyperparameter configurations, covering variations in time steps and epochs, to find the most optimal model. The model's performance was evaluated using the Mean Absolute Percentage Error (MAPE) metric. The results indicate that the best configuration, with 25 time steps and 100 epochs, achieved a MAPE value of 2.25%. This value signifies that the LSTM model has a very high level of accuracy (Highly Accurate) in predicting PTBA's stock price movements. This study confirms that an LSTM model optimized through hyperparameter tuning is a reliable tool for predicting highly volatile stock prices. Keywords: Stock Price Prediction, Long Short-Term Memory, LSTM, PTBA, MAPE Fluktuasi harga saham yang tinggi di sektor pertambangan menjadi tantangan bagi investor dalam pengambilan keputusan. Penelitian ini bertujuan untuk membangun dan mengevaluasi model prediksi harga saham PT Bukit Asam Tbk (PTBA) menggunakan metode Long Short-Term Memory (LSTM). Data yang digunakan adalah data historis harga penutupan harian PTBA dari 1 Januari 2014 hingga 31 Desember 2023 , yang dibagi menjadi 80% data pelatihan dan 20% data pengujian. Eksperimen dilakukan dengan menguji 16 konfigurasi hyperparameter yang berbeda, mencakup variasi time step dan epochs, untuk menemukan model yang paling optimal. Kinerja model dievaluasi menggunakan metrik Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa konfigurasi terbaik, yaitu dengan 25 time step dan 100 epochs, mampu menghasilkan nilai MAPE sebesar 2.25%. Nilai ini menunjukkan bahwa model LSTM memiliki tingkat akurasi yang sangat tinggi (Sangat Akurat) dalam memprediksi pergerakan harga saham PTBA. Penelitian ini menegaskan bahwa metode LSTM yang dioptimalkan melalui tuning hyperparameter merupakan alat yang andal untuk memprediksi harga saham dengan volatilitas tinggi. Kata kunci : Prediksi Harga Saham, Long Short-Term Memory, LSTM, PTBA, MAPE
Actions (login required)
![]() |
View Item |