Analisis Perbandingan Kinerja Model Machine Learning dalam Prediksi Harga Saham TLKM

Suyatna Suyatna; Adi Joko Satrio; Satrio Putra Pratama; Mamat Indarto; Fadillah Syarif; Fachry Amsury

doi:10.31004/riggs.v4i4.3476

Authors

Suyatna Suyatna Universitas Bina Sarana Informatika
Adi Joko Satrio Universitas Bina Sarana Informatika
Satrio Putra Pratama Universitas Bina Sarana Informatika
Mamat Indarto Universitas Bina Sarana Informatika
Fadillah Syarif Universitas Bina Sarana Informatika
Fachry Amsury Universitas Bina Sarana Informatika

DOI:

https://doi.org/10.31004/riggs.v4i4.3476

Keywords:

Prediksi Harga Saham, Machine Learning, Linear Regression, Random Forest, Neural Network, Cross Validation

Abstract

Penelitian ini bertujuan mengevaluasi tingkat kinerja model machine learning dalam memprediksi harga penutupan saham TLKM berdasarkan data historis periode 2005 hingga 2024. Tiga algoritma diterapkan, yaitu linear regression, random forest, dan neural network (MLP), yang masing-masing mewakili tingkat kompleksitas berbeda. Evaluasi dilakukan menggunakan teknik cross validation dengan tiga metrik utama, yakni R², MAE, dan RMSE, untuk menilai ketepatan serta stabilitas hasil prediksi. Hasil penelitian menunjukkan bahwa random forest memiliki performa paling unggul dibandingkan dua model lainnya karena mampu menghasilkan prediksi yang stabil, akurat, dan efisien pada berbagai variasi data. Model ini juga menunjukkan kemampuan generalisasi yang tinggi, di mana hasil prediksi pada data uji memiliki tingkat kesesuaian hampir sempurna dengan nilai aktual. Linear regression memberikan hasil yang baik dan efektif dalam mengenali pola hubungan linier antarvariabel, mencerminkan bahwa data saham TLKM memiliki kecenderungan hubungan yang relatif stabil antar atributnya. Neural network (MLP) memperlihatkan peningkatan kinerja setelah dilakukan hyperparameter tuning, terutama pada konfigurasi jumlah neuron dan lapisan tersembunyi yang tepat, namun efisiensi komputasi model ini masih lebih rendah karena proses pelatihannya memerlukan waktu yang lebih panjang serta sensitif terhadap perubahan parameter. keseluruhan, Random forest dinilai sebagai model paling optimal karena mampu menjaga keseimbangan antara akurasi, stabilitas, dan efisiensi komputasi. Temuan ini memperkuat potensi penerapan algoritma ensemble dalam analisis pasar modal sebagai pendekatan yang lebih adaptif terhadap data keuangan. Hasil penelitian diharapkan menjadi referensi bagi mahasiswa, peneliti, dan investor dalam mengembangkan model prediksi berbasis machine learning yang andal untuk mendukung pengambilan keputusan investasi berbasis data di pasar saham Indonesia.

Downloads

Download data is not yet available.

References

T. N. Bui, X. H. Nguyen, and K. T. Pham, “The Effect of Capital Structure on Firm Value: A Study of Companies Listed on the Vietnamese Stock Market,” Int. J. Financ. Stud., vol. 11, no. 3, 2023, https://doi.org/10.3390/ijfs11030100.

G. Karo, H. G. Barus, N. L. Salsabila, R. N. A. Harahap, R. Syahutra, and R. B. Rayoga, “Analyzing Factors Influencing Investment Decisions in the Indonesian Capital Market,” J. Ecoment Glob., vol. 10, no. 1, pp. 81–89, 2025, https://ejournal.uigm.ac.id/index.php/EG/article/download/5383/2520/16517.

E. S. Setiawan, “Pengaruh Debt to Equity Ratio, Earnings Per Share, dan Return On Equity terhadap Return Saham (Studi Pada Perusahaan Consumer Non-cyclical dan Consumer Cyclical yang Terdaftar di Bursa Efek Indonesia Tahun 2021-2022)”, Univ. Multimed. Nusant. Knowladge Cent., pp. 1–13, 2024, [Online]. Available: https://kc.umn.ac.id/id/eprint/34426/2/BAB_I.pdf

W. R. Murhadi, F. R. Kencanasar, and B. S. Sutedjo, “The Influence of Financial Literacy and Financial Interest on the Financial Risk Tolerance of Investor in Indonesia,” Journal of Law and Sustainable Development. Dev., vol. 11, no. 2, pp. 1–16, 2023, https://ojs.journalsdg.org/jlss/article/download/310/250/878.

I. D. Dichev and X. Zheng, “The volatility of stock investor returns,” J. Financ. Mark., vol. 70, p. 100927, 2024, https://doi.org/10.1016/j.finmar.2024.100927.

F. D. Sumaryana, N. Nugraha, M. Sari, and T. Heryawan, “The Influence of Macroeconomic Fundamentals and Investor Sentiment on the Indonesian Stock Exchange,” Atl. Press Int. BV, no. Gcbme 2023, pp. 7–13, 2024, doi: 10.2991/978-94-6463-443-3_2.

R. Rizky, P. Suwardi, E. Siska, and D. R. Sebastian, “Impact of Liquidity and Activity Ratios on Stock Price in Indonesia ’ s Telecom Companies,” J. Bus. Econ. Res., vol. 5, no. 3, pp. 495–503, 2024, https://doi.org/10.47065/jbe.v5i3.5910.

A. K. Dewa and S. Sundari, “Liquidity Amplifies, Dividends Stabilize: Evidence from Stock Price Volatility in Indonesia’s LQ45 Index,” Formosa Journal of Multidisciplinary Research, vol. 4, no. 8, pp. 3825–3840, 2025, https://npaformosapublisher.org/index.php/fjmr/article/download/380/437.

G. M. Tinungki, S. Siswanto, and A. Najiha, “The Gumbel Copula Method for Estimating Value at Risk: Evidence from Telecommunication Stocks in Indonesia during the COVID-19 Pandemic,” J. Risk Financ. Manag., vol. 16, no. 10, 2023, https://doi.org/10.3390/jrfm16100424.

B. Y. Dwiandiyanta, R. Hartanto, and R. Ferdiana, “Harnessing Deep Learning and Technical Indicators for Enhanced Stock Predictions of Blue-Chip Stocks on the Indonesia Stock Exchange (IDX),” Eng. Technol. Appl. Sci. Res., vol. 15, no. 1, pp. 20348–20357, 2025, https://doi.org/10.48084/etasr.9850.

Y. Huang, L. F. Capretz, and D. Ho, “Machine Learning for Stock Prediction Based on Fundamental Analysis,” 2021 IEEE Symp. Ser. Comput. Intell. SSCI 2021 - Proc., 2021, https://arxiv.org/pdf/2202.05702.

J. Zou et al., “Stock Market Prediction via Deep Learning Techniques: A Survey,” arxiv.org, vol. 1, no. 1, 2023, [Online]. Available: https://arxiv.org/abs/2212.12717.

M. Saberironaghi, J. Ren, and A. Saberironaghi, “Stock Market Prediction Using Machine Learning and Deep Learning Algorithms” Sustain. Digit. Technol. Smart Cities Heal. Commun. Transp., pp. 127–138, 2023, https://doi.org/10.1049/cit2.12059.

Y. Li, H. Xue, S. Wei, R. Wang, and F. Liu, “A Machine Learning Approach for Investigating the Determinants of Stock Price Crash Risk: Exploiting Firm and CEO Characteristics,” Systems, vol. 12, no. 5, 2024, https://doi.org/10.3390/systems12050143.

S. Ouf, M. El Hawary, A. Aboutabl, and S. Adel, “A Deep Learning-Based LSTM for Stock Price Prediction Using Twitter Sentiment Analysis,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 12, pp. 207–218, 2024, https://thesai.org/Downloads/Volume15No12/Paper_23-A_Deep_Learning_Based_LSTM_for_Stock_Price_Prediction.pdf.

T. Hall and K. Rasheed, “A Survey of Machine Learning Methods for Time Series Prediction,” Appl. Sci., vol. 15, no. 11, 2025, https://www.mdpi.com/2076-3417/15/11/5957/pdf.

X. Kong et al., “Deep learning for time series forecasting: a survey,” Int. J. Mach. Learn. Cybern., vol. 16, no. 7–8, pp. 5079–5112, 2025, https://doi.org/10.48550/arXiv.2503.10198.

W. Bao, Y. Cao, Y. Yang, H. Che, J. Huang, and S. Wen, “Data-driven stock forecasting models based on neural networks: A review,” Inf. Fusion, vol. 113, p. 102616, 2025, https://doi.org/10.1016/j.inffus.2024.102616.

M. Barua, T. Kumar, K. Raj, and A. M. Roy, “Comparative Analysis of Deep Learning Models for Stock Price Prediction in the Indian Market,” FinTech, vol. 3, no. 4, pp. 551–568, 2024, https://doi.org/10.3390/fintech3040029.

G. Campisi, S. Muzzioli, and B. De Baets, “A comparison of machine learning methods for predicting the direction of the US stock market on the basis of volatility indices,” International Journal of Forecasting, vol. 40, no. 3, pp. 869–880, 2024, https://doi.org/10.1016/j.ijforecast.2023.07.002.

S. Abolmakarem, F. Abdi, K. Khalili-Damghani, and H. Didehkhani, “A multi-stage machine learning approach for stock price prediction: Engineered and derivative indices,” Intell. Syst. with Appl., vol. 24, p. 200449, 2024, https://doi.org/10.1016/j.iswa.2024.200449.