Pemodelan Prediktif Harga Saham Menggunakan Simple Moving Average Dengan Metode Long Short-Term Memory
Kata Kunci:
saham, prediksi harga, LSTM, SMA, time seriesAbstrak
Pasar saham, khususnya di sektor tambang, memiliki volatilitas tinggi akibat berbagai faktor eksternal dan internal. Investor sering kesulitan memprediksi harga saham hanya dengan analisis fundamental karena tidak sepenuhnya menggambarkan dinamika perubahan harga. Analisis teknis menggunakan indikator Simple Moving Average (SMA) kerap dimanfaatkan untuk mengidentifikasi tren jangka pendek, namun kurang tanggap terhadap perubahan cepat. Pendekatan deep learning seperti Long Short- Term Memory (LSTM) mampu mempelajari pola jangka panjang dan nonlinear, sehingga berpotensi meningkatkan akurasi prediksi harga saham. Penelitian ini menggabungkan SMA dan LSTM untuk memprediksi harga saham empat perusahaan tambang terdaftar di LQ45. Hasil pengujian menunjukkan bahwa integrasi SMA tidak selalu meningkatkan akurasi. Pada ANTM, penambahan SMA menurunkan MAPE dari 5,01% menjadi 4,92%, namun pada INCO dan PTBA, akurasi justru menurun. Pada INCO, penambahan SMA menaikkan MAPE dari 5,55% menjadi 6,33%, sedangkan pada PTBA menaikkan MAPE dari 6,72% menjadi 7,52%. Sedangkan ADRO mengalami perubahan MAPE kecil dari 3,74% menjadi 3,86%. Dengan demikian, efektivitas SMA bergantung pada karakteristik masing-masing saham. LSTM tetap kompetitif bahkan tanpa SMA, sehingga penggunaan SMA harus dipertimbangkan secara kontekstual. Penelitian ini memperkaya wawasan dalam memprediksi harga saham di sektor tambang yang fluktuatif dan dapat membantu investor dalam pengambilan keputusan yang lebih tepat.
Referensi
Agrawal, M., Khan, A.U. dan Shukla, P.K., 2019. Stock price prediction using
technical indicators: A predictive model using optimal deep learning.
International Journal of Recent
Technology and Engineering, 8(2),
hal.2297–2305. https://doi.org/10.35940/ijrteB3048.078219.
Ayyadevara, V.K., 2018. Pro Machine Learning Algorithms.
Bursa Efek Indonesia, 2019.
Cahyaningrum, D., 2023. LARANGAN
EKSPOR SUMBER DAYA ALAM MINERAL MENTAH : NIKEL DAN BAUKSIT. XV(4).
Cao, J., Li, Z. dan Li, J., 2019. Financial time series forecasting model based on CEEMDAN and LSTM. Physica A:
Statistical Mechanics and its Applications, [daring] 519, hal.127–
https://doi.org/10.1016/j.physa.2018.11.061.
Chang, P.-C., Liu, C.-H., Yeh, C.-H. dan Chen, S.-H., 2006. The Development of a Weighted Evolving Fuzzy. [daring]
(June 2014). https://doi.org/10.1007/11816171.
Hayes, A., 2023. What Is Closing Price?
Definition, How It’s Used, and Example.
Hochreiter, S. dan Schmidhuber, J., 1997. Long Short-Term Memory. Neural Computation, [daring] 9(8), hal.1735–1780.
https://doi.org/10.1162/neco.1997.9.8.1735.
JAIN, Y.K. dan BHANDARE, S.K., 2013. Min Max Normalization Based Data
Perturbation Method for Privacy
Protection. International Journal of
Computer and Communication
Technology, [daring] 4(4), hal.233–238.
https://doi.org/10.47893/ijcct.2013.120
Kumar, V. dan Kaur, M., 2019. Stock Market Prediction Using Moving Average and Deep Learning Techniques. Journal of Finance and Data Science, 5(2), hal.72–82.
Lamabelawa, M.I.J., 2018. PERBANDINGAN INTERPOLASI DAN EKSTRAPOLASI NEWTON. JURNAL TEKNOLOGI INFORMASI, [daring] 10(2), hal.73–80. Tersedia pada: <https://publikasi.uyelindo.ac.id/index.php/hoaq/article/view/20/9>.
Luo, 2010. Research on strategy of moving average. Journal of Sichuan Economic Management Institute, 12, hal.40–42.
Makridakis, S. dan Hibon, M., 1995. Evaluating accuracy (or error) measures in forecasting. International Journal of Forecasting, 11(4), hal.669–670.
Murphy, C., 2010. Moving averages tutorial. [daring] Tersedia pada:
jmsc7008spring2012/files/2010/02/Mo
vingAverages.pdf>.
Novita, A., 2017. Prediksi Pergerakan Harga Saham Pada Bank Terbesar Di Indonesia Dengan Metode Backpropagation Neural Network.
jutisi: Jurnal Ilmiah Teknik Informatika
dan Sistem Informasi, 05(01), hal.965–
Ong, E., 2016. Technical Analysis for Mega Profit. Gramedia Pustaka Utama.
Permana, S.H., 2022. DAMPAK PERANG
RUSIA – UKRAINA TERHADAP PEREKONOMIAN INDONESIA.
Schlotmann, R. dan Czubatinski, M., 2019. Trading: Technical Analysis
Masterclass: Master the financial markets.
Souza, M.J.S. de, Ramos, D.G.F., Pena, M.G., Sobreiro, V.A. dan Kimura, H., 2018. Examination of the profitability of technical analysis based on moving
average strategies in BRICS.
THE INVESTOPEDIA TEAM, 2024. Opening Price: Definition, Example, Trading Strategies.
Wang, J., Zhang, X. dan Zhao, M., 2019. Stock Price Prediction Using LSTM with
Technical Indicators. In: Proceedings of the 2019 IEEE International Conference on Big Data. hal.2682–2690.
Zhang, X., Wang, H. dan Liu, J., 2020. A
comprehensive review of evaluation
metrics in predictive modeling. Journal
of Data Science, 18(2), hal.200–215.
Agrawal, M., Khan, A.U. dan Shukla, P.K., 2019. Stock price prediction using
technical indicators: A predictive model using optimal deep learning.
International Journal of Recent
Technology and Engineering, 8(2),
hal.2297–2305. https://doi.org/10.35940/ijrteB3048.078219.
Ayyadevara, V.K., 2018. Pro Machine Learning Algorithms.
Bursa Efek Indonesia, 2019.
Cahyaningrum, D., 2023. LARANGAN
EKSPOR SUMBER DAYA ALAM MINERAL MENTAH : NIKEL DAN BAUKSIT. XV(4).
Cao, J., Li, Z. dan Li, J., 2019. Financial time series forecasting model based on CEEMDAN and LSTM. Physica A:
Statistical Mechanics and its Applications, [daring] 519, hal.127–
https://doi.org/10.1016/j.physa.2018.11.061.
Chang, P.-C., Liu, C.-H., Yeh, C.-H. dan Chen, S.-H., 2006. The Development of a Weighted Evolving Fuzzy. [daring]
(June 2014). https://doi.org/10.1007/11816171.
Hayes, A., 2023. What Is Closing Price?
Definition, How It’s Used, and Example.
Hochreiter, S. dan Schmidhuber, J., 1997. Long Short-Term Memory. Neural Computation, [daring] 9(8), hal.1735–1780.
https://doi.org/10.1162/neco.1997.9.8.1735.
JAIN, Y.K. dan BHANDARE, S.K., 2013. Min Max Normalization Based Data
Perturbation Method for Privacy
Protection. International Journal of
Computer and Communication
Technology, [daring] 4(4), hal.233–238.
https://doi.org/10.47893/ijcct.2013.120
Kumar, V. dan Kaur, M., 2019. Stock Market Prediction Using Moving Average and Deep Learning Techniques. Journal of Finance and Data Science, 5(2), hal.72–82.
Lamabelawa, M.I.J., 2018. PERBANDINGAN INTERPOLASI DAN EKSTRAPOLASI NEWTON. JURNAL TEKNOLOGI INFORMASI, [daring] 10(2), hal.73–80. Tersedia pada: <https://publikasi.uyelindo.ac.id/index.php/hoaq/article/view/20/9>.
Luo, 2010. Research on strategy of moving average. Journal of Sichuan Economic Management Institute, 12, hal.40–42.
Makridakis, S. dan Hibon, M., 1995. Evaluating accuracy (or error) measures in forecasting. International Journal of Forecasting, 11(4), hal.669–670.
Murphy, C., 2010. Moving averages tutorial. [daring] Tersedia pada:
jmsc7008spring2012/files/2010/02/Mo
vingAverages.pdf>.
Novita, A., 2017. Prediksi Pergerakan Harga Saham Pada Bank Terbesar Di Indonesia Dengan Metode Backpropagation Neural Network.
jutisi: Jurnal Ilmiah Teknik Informatika
dan Sistem Informasi, 05(01), hal.965–
Ong, E., 2016. Technical Analysis for Mega Profit. Gramedia Pustaka Utama.
Permana, S.H., 2022. DAMPAK PERANG
RUSIA – UKRAINA TERHADAP PEREKONOMIAN INDONESIA.
Schlotmann, R. dan Czubatinski, M., 2019. Trading: Technical Analysis
Masterclass: Master the financial markets.
Souza, M.J.S. de, Ramos, D.G.F., Pena, M.G., Sobreiro, V.A. dan Kimura, H., 2018. Examination of the profitability of technical analysis based on moving
average strategies in BRICS.
THE INVESTOPEDIA TEAM, 2024. Opening Price: Definition, Example, Trading Strategies.
Wang, J., Zhang, X. dan Zhao, M., 2019. Stock Price Prediction Using LSTM with
Technical Indicators. In: Proceedings of the 2019 IEEE International Conference on Big Data. hal.2682–2690.
Zhang, X., Wang, H. dan Liu, J., 2020. A
comprehensive review of evaluation
metrics in predictive modeling. Journal
of Data Science, 18(2), hal.200–215.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer

Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.