eprintid: 51373 rev_number: 38 eprint_status: archive userid: 17817 dir: disk0/00/05/13/73 datestamp: 2025-07-15 02:59:41 lastmod: 2025-07-15 02:59:41 status_changed: 2025-07-15 02:59:41 type: thesis metadata_visibility: show contact_email: reztuzikri@gmail.com creators_name: Novdian, Mohamad Restu Zikri creators_id: 3337210007 contributors_type: http://www.loc.gov/loc.terms/relators/THS contributors_type: http://www.loc.gov/loc.terms/relators/THS contributors_name: Krisdianto, Nanang contributors_name: Ansori, Yulian contributors_id: 197504092006041004 contributors_id: 199007222024061001 corp_creators: UNIVERSITAS SULTAN AGENG TIRTAYASA corp_creators: FAKULTAS TEKNIK corp_creators: PROGRAM STUDI INFORMATIKA title: IMPLEMENTASI MODEL DEEP LEARNING DALAM MEMPREDIKSI HARGA SAHAM MENGGUNAKAN ALGORITMA GATED RECURRENT UNIT (GRU) (Studi Kasus Pada Perusahaan yang Terdaftar di IDXBUMN20 Tahun 2025) ispublished: pub subjects: T1 divisions: TKI full_text_status: restricted keywords: Analisis Sentimen, Deep learning, Gated Recurrent Unit (GRU), Prediksi Saham, Volatilitas Pasar abstract: Penelitian ini dilatarbelakangi oleh pentingnya prediksi harga saham yang akurat dalam dunia investasi. Pergerakan harga saham yang fluktuatif sering kali dipengaruhi oleh faktor-faktor seperti kinerja perusahaan, suku bunga, dan tingkat inflasi. Permasalahan dalam penelitian ini adalah bagaimana mengimplementasikan algoritma Gated Recurrent Unit (GRU) untuk memprediksi harga saham pada perusahaan yang terdaftar di indeks IDXBUMN20 dengan menggunakan data historis harga saham (open, close, low, high, volume), volatilitas harian, dan sentimen pasar yang diambil dari berita CNBC dianalisis menggunakan model VADER (Valence Aware Dictionary and sEntiment Reasoner). Penelitian ini menggunakan pendekatan kuantitatif dengan metode eksperimen. Tujuan penelitian ini adalah mengimplementasikan model deep learning untuk memprediksi harga saham menggunakan algoritma GRU dan menganalisis kontribusi masing-masing fitur terhadap performa model. Evaluasi model dilakukan menggunakan metrik Root Mean Square Error (RMSE) Mean Absolute Error (MAE), dan Mean Absolute Percentage Error (MAPE). Hasil penelitian menunjukkan bahwa model GRU memberikan akurasi prediksi yang baik, ditunjukkan oleh nilai MAPE yang berada pada kisaran 0,82% hingga 2,73%, RMSE Rp 6.95-Rp 129.29, MAE Rp 4.92 – Rp 102.58. Hasil analisis Feature Ablation Study menunjukkan bahwa fitur data historis dan volatilitas pasar berpengaruh dalam peningkatan akurasi prediksi, dibandingkan dengan fitur sentimen yang dapat dipertimbangkan penggunaan selanjutnya. Kesimpulan dari penelitian ini adalah algoritma GRU efektif digunakan dalam prediksi harga saham perusahaan yang terdaftar di indeks IDXBUMN20. date: 2025-06-20 date_type: published pages: 165 institution: Fakultas Teknik Universitas Sultan Ageng Tirtayasa department: Informatika thesis_type: sarjana thesis_name: sarjana referencetext: [1] W. Theresia and R. Rostiana, “Pengaruh literasi keuangan, pengetahuan investasi, dan faktor sosial terhadap minat berinvestasi saham Generasi Z,” Jurnal Manajemen Bisnis dan Kewirausahaan, vol. 8, no. 4, pp. 881–894, 2024. [Online]. Available: https://doi.org/10.24912/jmbk.v8i4.31640 [2] L. Sari, R. Septiano, and B. Pramadian, “Dampak inflasi terhadap fluktuasi harga saham perbankan di Indonesia: Analisis data tahun 2017–2023,” Journal of Social and Economics Research, vol. 6, no. 2, pp. 1014–1023, 2024. [3] F. Adrianto and M. Hamidi, “Analysis of retail investment behavior in Indonesian stock market,” Academy of Entrepreneurship Journal, vol. 24, no. 2,pp.1–9,2020.[Online].Available: https://www.abacademies.org/articles/analysis-of-retail-investment-behavior-in-indonesian-stock-market-9871.html [4] K. N. F. Syahnur, D. F. Surianto, and M. T. Dharsana, “Analysis of retail sector market reaction in Indonesia on social media and investor sentiment,” Jurnal Manajemen Bisnis, vol. 10, no. 2, pp. 371–383, 2023. [5] Kustodian Sentral Efek Indonesia, Statistik Pasar Modal Indonesia 2024. 2024.[Online].Available: https://www.ksei.co.id/files/Statistik_Publik_Desember_2024_v3.pdf. [Accessed: Dec. 20, 2024, 09:00 WIB]. [6] E. Pajrianti, R. S. Wardhani, and A. Yunita, “Analisis komparatif abnormal return dan trading volume activity sebelum dan sesudah pemilihan umum serentak tahun 2024 (Perusahaan yang tercatat di IDXBUMN20),” Innovative: Journal of Social Science Research, vol. 4, no. 3, pp. 10592–10604, 2024. [7] I. Hendarsih and S. Harjunawati, “Penggolongan saham blue chip berdasarkan kapitalisasi pasar pada Bursa Efek Indonesia tahun 2017–2020,” Akrab Juara: Jurnal Ilmu-ilmu Sosial, vol. 5, no. 2, pp. 115–133, 2020. [8] P. R. Pangestuti, “Pengaruh profitabilitas, struktur modal dan ukuran perusahaan terhadap harga saham pada perusahaan IDXBUMN20 yang terdaftar di BEI tahun 2019–2023”, Doctoral dissertation, Universitas Putra Bangsa, 2024. [9] M. F. Mahfuzh and R. V. Yuliantari, “Analisis penerapan artificial neural network algoritma propagasi balik untuk meramalkan harga saham pada Bursa Efek Indonesia,” Journal of Applied Electrical Engineering, vol. 6, no. 1, pp. 1–3, 2022. [Online]. Available: https://doi.org/10.30871/jaee.v6i1.3814. [10] K. Sofi, A. S. Sunge, S. R. Riady, and A. Z. Kamalia, “Perbandingan algoritma linear regression, LSTM, dan GRU dalam memprediksi harga saham dengan model time series,” Prosiding SeminaStika, vol. 3, no. 1, pp. 39–46, 2021. [11] M. Marwondo and T. Hidayah, “Perbandingan algoritma Long Short-Term Memory (LSTM) dan Gated Recurrent Unit (GRU) untuk prediksi harga emas dunia,” Search (Informatic, Science, Entrepreneur, Applied Art, Research, Humanism), vol. 21, no. 2, pp. 230–239, 2022. [12] A. Arfan and L. E. T. P., “Perbandingan algoritma Long Short-Term Memory dengan SVR pada prediksi harga saham di Indonesia,” Petir, vol. 13, no. 1, pp. 33–43, 2020. [Online]. Available: https://doi.org/10.33322/petir.v13i1.858. [13] B. H. Mahendra, L. Chaerani, and G. Marliza Gane, “Analisis perbandingan prediksi harga saham menggunakan algoritma artificial neural network dan linear regression,” Jurnal Ilmiah Komputasi, vol. 22, no. 2, 2023. [Online]. Available: https://doi.org/10.32409/jikstik.22.2.3357. [14] A. Yunizar, T. Rismawan, and D. M. Midyanti, “Penerapan metode Recurrent Neural Network model Gated Recurrent Unit untuk prediksi harga cryptocurrency,” Coding: Jurnal Komputer dan Aplikasi, vol. 11, no. 1, pp. 32–41, 2023. [15] Bursa Efek Indonesia, Panduan Investasi Saham. 2024. [Online]. Available: https://www.idx.co.id/. [Accessed: Dec. 20, 2024, 09:00 WIB]. [16] H. Romli, M. Febrianti, and T. S. Pratiwi, “Faktor-faktor yang mempengaruhi volatilitas harga saham pada PT Waskita Karya Tbk,” Jurnal Ilmiah Ekonomi Global Masa Kini, vol. 8, no. 1, pp. 1–5, 2017. [17] H. Rosyida, A. Firmansyah, and S. B. Wicaksono, “Volatilitas harga saham: leverage, ukuran perusahaan, pertumbuhan aset,” JAS (Jurnal Akuntansi Syariah), vol. 4, no. 2, pp. 196–208, 2020. [18] K. R. Selpiana and I. B. Badjra, “Pengaruh kebijakan dividen, nilai tukar, leverage, dan firm size terhadap volatilitas harga saham,” E-Jurnal Manajemen Universitas Udayana, vol. 7, no. 3, p. 1682, 2018. [19] N. Iryani and L. M. Yahya, “Pengaruh Fama and French model, sentimen pasar, makro ekonomi dan momentum terhadap pengembalian saham,” Jambura Journal of Community Empowerment, pp. 53–61, 2024. [20] H. A. Utami, E. Herwiyanti, and I. Suparlinah, “Pengaruh sentimen pasar terhadap pergerakan harga saham pada perusahaan industri manufaktur pada Bursa Efek Indonesia,” Jurnal Ekonomi, Bisnis, dan Akuntansi, vol. 26, no. 1, pp. 25–34, 2024. [21] F. Razi and Nurdin, “Pengaruh analisis teknikal dan analisis rasio fundamental terhadap harga saham,” Bandung Conference Series: Business and Management, vol. 4, no. 1, pp. 439–446, 2024. [Online]. Available: https://doi.org/10.29313/bcsbm.v4i1.11104. [22] F. M. Shiri, T. Perumal, N. Mustapha, and R. Mohamed, “A comprehensive overview and comparative analysis on deep learning models: CNN, RNN, LSTM, GRU,” arXiv preprint, arXiv:2305.17473, 2023. [Online]. Available: https://arxiv.org/abs/2305.17473. [23] S. Muis, Jaringan Syaraf Tiruan: Sistem Kecerdasan Tiruan dengan Kemampuan Belajar dan Adaptasi. Yogyakarta: Teknosain, 2017. [24] X. Song, Y. Liu, L. Xue, J. Wang, J. Zhang, J. Wang, L. Jiang, and Z. Cheng, “Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model,” Journal of Petroleum Science and Engineering, vol. 186, p. 106682, 2020. [Online]. Available: https://doi.org/10.1016/j.petrol.2019.106682. [25] S. Elsworth and S. Güttel, “Time series forecasting using LSTM networks: A symbolic approach,” arXiv preprint, arXiv:2003.05672, 2020. [Online]. Available: http://arxiv.org/abs/2003.05672. [26] S. Zahir, Peramalan multi parameter untuk data time series saham menggunakan LSTM dan model pembelajaran mendalam, 2023, pp. 1–24. [27] A. M. Harahap and S. Fitrie, “Implementasi Gated Recurrent Unit (GRU) untuk prediksi harga saham bank konvensional di Indonesia,” JISTech (Journal of Islamic Science and Technology), vol. 6, no. 2, pp. 42–49, 2021. [Online]. Available: http://jurnal.uinsu.ac.id/index.php/jistech. [28] V. R. Danestiara, E. Setiana, I. Akbar, and T. Hidayah, “Algoritma Gated Recurrent Unit untuk prediksi harga indeks penutupan saham LQ45,” Jurnal Accounting Information System (AIMS), vol. 7, no. 1, pp. 1–8, 2024. [29] A. Nilsen, Implementasi model Gated Recurrent Unit dalam memprediksi harga saham, Skripsi Sarjana, Fakultas Matematika dan Ilmu Pengetahuan Alam, Universitas Indonesia, Depok, 2020. [30] R. H. Sulaiman, I. M. A. D. Suarjaya, and A. A. K. A. C. Wiranatha, “Optimalisasi formula default pada Amibroker untuk analisis teknikal pada pasar saham,” Jurnal Ilmiah Merpati (Menara Penelitian Akademika Teknologi Informasi), vol. 8, no. 3, p. 177, 2020. [Online]. Available: https://doi.org/10.24843/jim.2020.v08.i03.p03. [31] J. Deveikyte, H. Geman, C. Piccari, and A. Provetti, “A sentiment analysis approach to the prediction of market volatility,” Frontiers in Artificial Intelligence, vol. 5, pp. 1–15, 2022. [Online]. Available: https://doi.org/10.3389/frai.2022.836809.. [32] T. Pano and R. Kashef, “A complete VADER-based sentiment analysis of Bitcoin (BTC) tweets during the era of COVID-19,” Big Data and Cognitive Computing, vol. 4, no. 4, pp. 1–17, 2020. [Online]. Available: https://doi.org/10.3390/bdcc4040033. [33] N. M. Janna, “Variabel dan skala pengukuran statistik,” Dec. 13, 2020. [Online]. Available: https://doi.org/10.31219/osf.io/8326r. [34] D. Zhuang, X. Zhang, S. Song, and S. Hooker, “Randomness in neural network training: Characterizing the impact of tooling,” Proceedings of Machine Learning and Systems, vol. 4, pp. 316–336, 2022. [35] R. Meyes, M. Lu, C. W. de Puiseau, and T. Meisen, “Ablation studies in artificial neural networks,” arXiv preprint, arXiv:1901.08644, 2019. [Online]. Available: https://arxiv.org/abs/1901.08644. [36] I. A. Sah, “Volatilitas pasar saham dan indikator makroekonomi: Analisis sektor keuangan di tengah optimisme pertumbuhan ekonomi,” Jurnal Ekonomi, Bisnis dan Pendidikan, vol. 5, no. 2, 2025. [Online]. Available: https://doi.org/10.17977/um066.v5.i2.2025.1.. [37] A. Gupta and R. Mishra, “A comprehensive study of stock market volatility: Types, determinants, and measurement methods,” International Journal for Multidisciplinary Research (IJFMR), vol. 6, no. 6, Nov.–Dec. 2024. [38] C. Hutto and E. Gilbert, "VADER: A parsimonious rule-based model for sentiment analysis of social media text," in Proceedings of the International AAAI Conference on Web and Social Media, vol. 8, no. 1, pp. 216–225, May 2014. [39] I. S. Kervanci, M. F. Akay, and E. Özceylan, “Bitcoin price prediction using LSTM, GRU and hybrid LSTM-GRU with Bayesian optimization, random search, and grid search for the next days,” Journal of Industrial and Management Optimization, vol. 20, no. 2, pp. 570–588, 2024. [Online]. Available: https://doi.org/10.3934/jimo.2023091. [40] R. S. Andromeda and N. A. S. Winarsih, “Performance comparison of LSTM and GRU methods in predicting cryptocurrency closing prices,” Sistemasi: Jurnal Sistem Informasi, vol. 14, no. 1, pp. 366–379, 2025. [41] X. Lu, S. Y. Teh, C. J. Tay, N. F. A. Kassim, P. S. Fam, and E. Soewono, “Application of multiple linear regression model and long short-term memory with compartmental model to forecast dengue cases in Selangor, Malaysia based on climate variables,” Infectious Disease Modelling, vol. 10, no. 1, pp. 240–256, 2025. [42] I. N. Setiawan, R. Kurniawan, B. Yuniarto, R. E. Caraka, and B. Pardamean, “Parameter optimization of support vector regression using Harris hawks optimization,” Procedia Computer Science, vol. 179, pp. 17–24, 2021. [43] W. Freeborough and T. van Zyl, “Investigating explainability methods in recurrent neural network architectures for financial time series data,” Applied Sciences, vol. 12, no. 3, p. 1427, 20 citation: Novdian, Mohamad Restu Zikri (2025) IMPLEMENTASI MODEL DEEP LEARNING DALAM MEMPREDIKSI HARGA SAHAM MENGGUNAKAN ALGORITMA GATED RECURRENT UNIT (GRU) (Studi Kasus Pada Perusahaan yang Terdaftar di IDXBUMN20 Tahun 2025). S1 thesis, Fakultas Teknik Universitas Sultan Ageng Tirtayasa. document_url: https://eprints.untirta.ac.id/51373/19/Mohamad%20Restu%20Zikri%20Novdian_3337210007_Fulltext.pdf document_url: https://eprints.untirta.ac.id/51373/20/Mohamad%20Restu%20Zikri%20Novdian_3337210007_01.pdf document_url: https://eprints.untirta.ac.id/51373/3/Mohamad%20Restu%20Zikri%20Novdian_3337210007_02.pdf document_url: https://eprints.untirta.ac.id/51373/4/Mohamad%20Restu%20Zikri%20Novdian_3337210007_03.pdf document_url: https://eprints.untirta.ac.id/51373/5/Mohamad%20Restu%20Zikri%20Novdian_3337210007_04.pdf document_url: https://eprints.untirta.ac.id/51373/6/Mohamad%20Restu%20Zikri%20Novdian_3337210007_05.pdf document_url: https://eprints.untirta.ac.id/51373/7/Mohamad%20Restu%20Zikri%20Novdian_3337210007_Ref.pdf document_url: https://eprints.untirta.ac.id/51373/8/Mohamad%20Restu%20Zikri%20Novdian_3337210007_Lamp.pdf document_url: https://eprints.untirta.ac.id/51373/9/Mohamad%20Restu%20Zikri%20Novdian_3337210007_CP.pdf