PENDEKATAN KNN REGRESSION UNTUK PREDIKSI SAHAM GAMESTOP

Authors

  • Teo Sunu Widiantoro Universitas Nusantara PGRI Kediri Indonesia
  • Risky Aswi Ramadhani Universitas Nusantara PGRI Kediri Indonesia
  • Daniel Swanjaya Universitas Nusantara PGRI Kediri Indonesia

DOI:

https://doi.org/10.29407/jpers098

Abstract

Abstrak Prediksi saham memiliki peran penting dalam membantu investor dan pelaku pasar membuat keputusan investasi yang cerdas. Dalam penelitian ini, diterapkan algoritma KNN Regression (K-Nearest Neighbors Regression) untuk melakukan prediksi pergerakan saham perusahaan GameStop (GME). Metode KNN Regression memanfaatkan data historis dengan mencari sejumlah tetangga terdekat yang memiliki karakteristik serupa untuk memperkirakan nilai masa depan, sehingga mampu menyesuaikan diri dengan pola non-linear pada data saham. Evaluasi dan pengujian akurasi prediksi dilakukan menggunakan metrik MSE (Mean Squared Error) dan R² (Koefisien Determinasi). Data historis saham GameStop dikumpulkan dari sumber daring dan dipreproses sebagai input untuk algoritma KNN Regression. Hasil penelitian menunjukkan bahwa nilai parameter terbaik diperoleh pada K = 3, dengan nilai MSE sebesar 0.1 dan R² sebesar 0.98. Nilai MSE yang rendah dan R² yang tinggi mengindikasikan bahwa model mampu memprediksi harga saham dengan akurasi yang sangat baik dan menjelaskan 98% variansi dalam data. Melalui penggunaan metrik ini, dapat dievaluasi bahwa model prediksi memiliki performa yang optimal dalam konteks data saham GameStop. Penelitian ini memberikan gambaran tentang efektivitas KNN Regression dalam analisis prediktif saham GameStop serta membuka peluang untuk peningkatan model di masa mendatang.

Keywords:

KNN Regression, Prediksi Saham, Machine Learning, MSE, R2

##plugins.themes.default.displayStats.downloads##

##plugins.themes.default.displayStats.noStats##

References

[1] dan H. D. C. I. A. A. Saputra, M. R. Sidiq, S. S. Guritno, “Stock prediction performance optimization: enhancing covariance matrix with KNN,” J. Tek. Inform., vol. 5, no. 6, 2024, doi: 10.52436/1.jutif.2024.5.6.2399.

[2] Z. Chen, “Stock price forecasts based on KNN and LSTM,” Adv. Econ. Manag. Polit. Sci., vol. 55, hal. 70–77, doi: 10.54254/2754-1169/56/20231064.

[3] and A. D. S. Ghosh, R. S. Acharya, “A Comparative Study of KNN and SVR for Stock Market Forecasting,” Procedia Comput. Sci., vol. 191, hal. 422–429, 2021, doi: 10.1016/j.procs.2021.07.054.

[4] V. G. Kowti, “Stock price prediction using LSTM and KNN algorithms,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 11, no. 9, doi: 10.22214/ijraset.2023.55894.

[5] Y. Huang, “Research on the Google stock price prediction based on SVR, random forest, and KNN models,” Highlights Business, Econ. Manag., 2023, doi: 10.54097/n8hxqx19.

[6] dan A. P. L. A. Kharis, A. H. Zili, M. Malik, W. Nuryaningrum, “Comparing machine learning models for Indonesia stock market prediction,” IJEECS, vol. 38, no. 1, hal. 508–516, 2020, doi: 10.11591/ijeecs.v38.i1.pp508-516.

[7] dan Y. Z. S. Yu, Q. Zhang, “S&P 500 trend prediction,” Dec. 16, 2024. https://arxiv.org/abs/2401.03417

[8] Y. Alparslan dan E. Kim, “Extreme volatility prediction in stock market: When GameStop meets long short-term memory networks,” Mar. 1, 2021. https://arxiv.org/abs/2103.08608

[9] dan Y. Y. Y. Wang, Y. Xie, Y. Wu, “Improved KNN-based stock price prediction,” Acad. J. Comput. Inf. Sci, vol. 7, no. 6, 2024, doi: 10.25236/AJCIS.2024.070606.

[10] Kus Indrani Listyoningrum, Danise Yunaini Fenida, dan Nurhasan Hamidi, “Inovasi Berkelanjutan dalam Bisnis: Manfaatkan Flowchart untuk Mengoptimalkan Nilai Limbah Perusahaan,” J. Inf. Pengabdi. Masy., vol. 1, no. 4, hal. 100–112, 2023, doi: 10.47861/jipm-nalanda.v1i4.552.

Downloads

Published

2025-07-10

Issue

Vol. 9 No. 2 (2025): Prosiding Seminar Nasional Inovasi Teknologi Tahun 2025

Section

Articles

License

Copyright (c) 2025 Teo Sunu Widiantoro, Risky Aswi Ramadhani, Daniel Swanjaya

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Authors who publish with this journal agree to the following terms:

  1. Copyright on any article is retained by the author(s).
  2. The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work’s authorship and initial publication in this journal.
  3. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal’s published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
  4. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
  5. The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License

How to Cite

PENDEKATAN KNN REGRESSION UNTUK PREDIKSI SAHAM GAMESTOP. (2025). Prosiding SEMNAS INOTEK (Seminar Nasional Inovasi Teknologi), 9(2), 1373-1381. https://doi.org/10.29407/jpers098