Comparative Evaluation of Machine Learning Methods for Predicting Stock Price Changes
Abstract
Forecasting price patterns in the stock market poses a complicated and intricate task due to numerous uncertain factors and variables that influence market value. This study conducts a comparative evaluation of three popular computational learning approaches, namely Random Forest, K-Nearest Neighbors (KNN), and XGBoost, for predicting stock price changes. The research findings indicate that Random Forest achieves higher ROC scores, while XGBoost exhibits superior performance in relation to accuracy, recall, and precision. The Windowing method is also applied to the dataset to address overfitting issues. This study offers valuable knowledge for professionals and researchers in the domain of stock price prediction, enabling them to choose the optimal model based on preferred evaluation metrics.
Downloads
References
[2]Meidiawati, K., & Mildawati, T. (Februari, 2016). Pengaruh size, growth, profitabilitas, struktur modal, kebijakan dividen terhadap nilai perusahaan. Jurnal Ilmu Dan Riset Akuntansi (JIRA). [Online]. 5(2). Tersedia : http://jurnalmahasiswa.stiesia.ac.id/index.php/jira/article/view/1536
[3]Devitra, J. (Juni, 2013). Kinerja Keuangan dan Efisiensi Terhadap Return Saham Perbankan di Bursa Efek Indonesia Periode 2007-2011. Jurnal Keuangan dan Perbankan. [Online]. 15(1), hal. 38–53. Tersedia : https://journal.perbanas.id/index.php/jkp/article/view/181
[4]Mariana, S, “Pengaruh Faktor Fundamental, Faktor Teknikal Dan Risiko Sistematik Terhadap Harga Saham Pada Sektor Perbankan Indeks InfoBank15 Yang Terdaftar Di Bursa Efek Indonesia Periode 2015-2018,” disertasi doctor, Program Studi Magister Akuntansi, Sekolah Pasca Sarjana Universitas Widyatama, Indonesia, 2020.
[5]Khaidem, L., Saha, S., & Dey, S. R. (April, 2016). Predicting the direction of stock market prices using random forest. [Online]. arXiv preprint arXiv:1605.00003. Tersedia : https://arxiv.org/abs/1605.00003
[6]Breiman, L. (Oktober, 2001). Random forests. Machine learning. [Online]. 45, hal. 5–32. Tersedia : https://link.springer.com/article/10.1023/a:1010933404324
[7]Cutler, D. R., Edwards Jr, T. C., Beard, K. H., Cutler, A., Hess, K. T., Gibson, J., & Lawler, J. J. (November, 2007). Random forests for classification in ecology. Ecology. [Online]. 88(11), hal. 2783–2792. Tersedia : https://esajournals.onlinelibrary.wiley.com/doi/abs/10.1890/07-0539.1
[8]Chen, T., dan Guestrin, C, “Xgboost: A scalable tree boosting system”. Dalam Proc. 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, hal. 785-794.
[9]Cover, T., & Hart, P. (Januari, 1967). Nearest neighbour pattern classification. IEEE transactions on information theory. [Online]. 13(1), hal. 21–27. Tersedia : https://ieeexplore.ieee.org/document/1053964
[10]Wahyuni, R. E. (Juli, 2021). Optimasi Prediksi Inflasi dengan Neural Network Pada Tahap Windowing: Adakah Pengaruh Terhadap Window Size?. Jurnal Ilmiah “Technologia”. [Online]. 12(3). Hal. 176–181. Tersedia : https://ojs.uniska-bjm.ac.id/index.php/JIT/article/view/5181
[11]Fawcett, T. (Juni, 2006). An introduction to ROC analysis. Pattern Recognition Letters. [Online]. 27(8), hal. 861–874. Tersedia : https://www.sciencedirect.com/science/article/abs/pii/S016786550500303X
Copyright (c) 2024 Antivirus : Jurnal Ilmiah Teknik Informatika
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:
- Copyright on any article is retained by the author(s).
- Author grant 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 acknowledgement of the work’s authorship and initial publication in this journal.
- 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 acknowledgement of its initial publication in this journal.
- 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
