PIPELINE HADOOP–SPARK UNTUK ANALISIS DAN PREDIKSI SAHAM LQ45
ADOOP–SPARK PIPELINE FOR ANALYSIS AND PREDICTION OF LQ45 STOCK PRICES
DOI:
https://doi.org/10.52972/hoaq.vol17no2.p430-440Keywords:
big data, apache hadoop, apache spark, saham lq45, machine learningAbstract
Data pasar modal tumbuh cepat seiring meningkatnya transaksi saham secara digital. Namun, penelitian prediksi saham LQ45 umumnya berfokus pada model dan belum membahas infrastruktur pengolah datanya. Penelitian ini bertujuan merancang dan mengimplementasikan pipeline Big Data berbasis Apache Hadoop dan Apache Spark untuk menganalisis dan memprediksi pergerakan harga saham LQ45. Penelitian menggunakan pendekatan kuantitatif eksperimental. Data harian 45 emiten LQ45 periode Juni 2021–Juni 2026 dikumpulkan melalui API ingestion, disimpan di HDFS, lalu diproses dengan Spark. Tahap pemrosesan meliputi preprocessing, analisis deskriptif, serta pemodelan regresi dan klasifikasi dengan Spark MLlib. Hasil penelitian menunjukkan empat temuan utama. Pertama, pipeline mampu mengolah 53.682 baris data, dan format Parquet menghemat ruang penyimpanan sekitar 87%. Kedua, sektor Teknologi memiliki rentang harga harian tertinggi tetapi return terendah. Ketiga, Linear Regression menjadi model regresi terbaik dengan R² 0,9992. Keempat, akurasi seluruh model klasifikasi arah hanya sekitar 57%. Simpulannya, infrastruktur Hadoop–Spark layak diterapkan untuk analitik pasar modal. Nilai R² yang tinggi terutama mencerminkan persistensi harga harian, sedangkan arah pergerakan harga tetap sulit diprediksi.
Capital market data grow rapidly as digital stock trading increases. However, previous LQ45 stock prediction studies mostly focus on models and rarely address the underlying data processing infrastructure. This study aims to design and implement a Big Data pipeline based on Apache Hadoop and Apache Spark to analyze and predict LQ45 stock price movements. A quantitative experimental approach was used. Daily data of 45 LQ45 constituents from June 2021 to June 2026 were collected through API ingestion, stored in HDFS, and processed with Spark. The processing stages include preprocessing, descriptive analysis, and regression and classification modeling with Spark MLlib. The results show four main findings. First, the pipeline processed 53,682 records, and the Parquet format reduced storage space by about 87%. Second, the Technology sector had the highest daily price range but the lowest return. Third, Linear Regression was the best regression model with an R² of 0.9992. Fourth, all direction classification models achieved only about 57% accuracy. In conclusion, a Hadoop–Spark infrastructure is feasible for capital market analytics. The high R² mainly reflects daily price persistence, whereas the direction of price movement remains difficult to predict.
References
M. M. Hasan, J. Popp, and J. Oláh, “Current Landscape and Influence of Big Data on Finance,” Journal of Big Data, vol. 7, no. 1, pp. 1–17, Mar. 2020, doi: 10.1186/s40537-020-00291-z.
S. Gu, B. Kelly, and D. Xiu, “Empirical Asset Pricing Via Machine Learning,” The Review of Financial Studies, vol. 33, no. 5, pp. 2223–2273, May 2020, doi: 10.1093/rfs/hhaa009.
T. Fischer and C. Krauss, “Deep Learning With Long Short-Term Memory Networks for Financial Market Predictions,” European Journal of Operational Research, vol. 270, no. 2, pp. 654–669, Oct. 2018, doi: 10.1016/j.ejor.2017.11.054.
M. Zaharia, R. S. Xin, P. Wendell, T. Das, M. Armbrust, A. Dave, X. Meng, J. Rosen, S. Venkataraman, H. Franklin, A. Ghodsi, J. Gonzalez, S. Shenker, and I. Stoica, “Apache Spark: A Unified Engine for Big Data Processing,” Commun. ACM, vol. 59, no. 11, pp. 56–65, Nov. 2016, doi: 10.1145/2934664.
V. Belov, A. N. Kosenkov, and E. Nikulchev, “Experimental Characteristics Study of Data Storage Formats for Data Marts Development Within Data Lakes,” Applied Sciences, vol. 11, no. 18, pp. 1–9, Sep. 2021, doi: 10.3390/app11188651.
G. Achyar and O. Rohaeni, “Penggunaan Hybrid K-Means dan General Regression Neural Network untuk Prediksi Harga Saham Indeks LQ45,” Jurnal Riset Matematika, vol. 2, no. 2, pp. 111–120, Dec. 2022, doi: 10.29313/jrm.v2i2.1193.
K. Valiant, Y. Lukito, and R. G. Santosa, “Sistem Prediksi Harga Saham LQ45 dengan Random Forest Classifier,” Jurnal Terapan Teknologi Informasi, vol. 3, no. 2, pp. 127–136, Oct. 2019, doi: 10.21460/jutei.2019.32.187.
S. Hansun and J. C. Young, “Predicting LQ45 Financial Sector Indices Using RNN-LSTM,” Journal of Big Data, vol. 8, no. 1, pp. 1–13, Aug. 2021, doi: 10.1186/s40537-021-00495-x.
W. Budiharto, “Data Science Approach to Stock Prices Forecasting in Indonesia During Covid-19 Using Long Short-Term Memory (LSTM),” Journal of Big Data, vol. 8, no. 1, pp. 1–9, Mar. 2021, doi: 10.1186/s40537-021-00430-0.
Indra, S. Supian, Sukono, Riaman, M. P. A. Saputra, A. S. Azahra, and D. I. Pirdaus, “Stock Return Prediction on the LQ45 Market Index in the Indonesia Stock Exchange Using a Machine Learning Algorithm Based on Technical Indicators,” Journal of Risk and Financial Management, vol. 18, no. 12, pp. 1–33, Dec. 2025, doi: 10.3390/jrfm18120714.
E. Fitri and D. Riana, “Analisa Perbandingan Model Prediction dalam Prediksi Harga Saham Menggunakan Metode Linear Regression, Random Forest Regression dan Multilayer Perceptron,” METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi, vol. 6, no. 1, pp. 69–78, Apr. 2022, doi: 10.46880/jmika.Vol6No1.pp69-78.
N. Yeldho, D. Thomas, V. G. Kurian, C. Arathy, and A. V. N. Biju, “Are Machine Learning Models Effective in Predicting Emerging Markets? Investigating the Accuracy of Predictions in Emerging Stock Market Indices,” Quality & Quantity, vol. 59, no. 1, pp. 839–904, Feb. 2025, doi: 10.1007/s11135-024-01964-0.
E. F. Fama, “Efficient Capital Markets: A Review of Theory and Empirical Work,” The Journal of Finance, vol. 25, no. 2, pp. 383–417, May 1970, doi: 10.2307/2325486.
T. Phuoc, P. T. K. Anh, P. H. Tam, and C. V. Nguyen, “Applying Machine Learning Algorithms to Predict the Stock Price Trend in the Stock Market – The Case of Vietnam,” Humanities and Social Sciences Communications, vol. 11, no. 1, pp. 1–18, Mar. 2024, doi: 10.1057/s41599-024-02807-x.
X. Wei, Y. Tian, N. Li, and H. Peng, “Evaluating Ensemble Learning Techniques for Stock Index Trend Prediction: A case of China,” Portuguese Economic Journal, vol. 23, no. 3, pp. 505–530, Sep. 2024, doi: 10.1007/s10258-023-00246-1.
V. Cerqueira, L. Torgo, and I. Mozeti?, “Evaluating Time Series Forecasting Models: An Empirical Study on Performance Estimation Methods,” Machine Learning, vol. 109, no. 11, pp. 1997–2028, Nov. 2020, doi: 10.1007/s10994-020-05910-7.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi

This work is licensed under a Creative Commons Attribution 4.0 International License.
Jurnal HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi diterbitkan berdasarkan lisensi Creative Commons Attribution 4.0 International License (CC BY 4.0). Lisensi ini memungkinkan setiap orang untuk Berbagi: menyalin dan mendistribusikan kembali materi ini dalam format atau bentuk apapun; Adaptasi: merombak, mengubah, dan membuat turunan dari materi ini untuk keperluan apa pun, termasuk keperluan komersial, asalkan mereka memberikan pengakuan kepada Penulis Asli atas hasil karya aslinya.












