Imtiyaz, Rana Athaya (2025) Peramalan Interval Arah Pergerakan Harga Saham dengan Input Indikator Teknikal Menggunakan Quantile Regression Neural Network (QRNN) dan Hybrid LASSO-QRNN. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6003232016-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6003232016-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (11MB) | Request a copy |
Abstract
Pasar modal di Indonesia mengalami pertumbuhan signifikan dalam jumlah investor dari tahun 2021 hingga 2024, salah satu sektor yang paling diminati adalah sektor keuangan khususnya perusahaan perbankan. Pergerakan harga saham perbankan bersifat fluktuatif dan dipengaruhi oleh berbagai faktor, sehingga memprediksi arah pergerakannya menjadi tantangan bagi investor. Penelitian ini bertujuan untuk meramalkan interval arah pergerakan harga saham tiga emiten perbankan yang terdiri dari BBCA, BRIS, dan ARTO menggunakan pendekatan Quantile Regression Neural Network (QRNN) dan Hybrid LASSO-QRNN dengan mempertimbangkan variabel input yaitu indikator teknikal. QRNN dipilih karena kemampuannya menangani distribusi data yang nonlinier, sementara Hybrid LASSO-QRNN menggabungkan Least Absolute Shrinkage and Selection Operator (LASSO) yang merupakan metode seleksi variabel pada model Quantile Regression dengan tujuan meningkatkan akurasi prediksi dan mengurangi overfitting. Penelitian ini menggunakan data time series dengan periode waktu 1 Maret 2021 sampai 24 Januari 2025 dan menerapkan horizon 5, 10, dan 22 hari perdagangan. Berdasarkan hasil evaluasi QRMSE dan QMAE, model hybrid LASSO-QRNN menunjukkan peningkatan performa pada pada kuantil 50% sebagian besar saham dan horizon, terutama pada saham BBCA.
===============================================================================================================================
The Indonesian capital market has experienced significant growth in the number of investors from 2021 to 2024, with the financial sector, particularly banking companies, being one of the most attractive sectors. The stock price movements of banking companies are highly volatile and influenced by various factors, making it challenging for investors to predict their direction. This study aims to forecast the interval of stock price movement directions for three banking sector stocks BBCA, BRIS, and ARTO using the Quantile Regression Neural Network (QRNN) and Hybrid LASSO-QRNN approaches while considering technical indicators as input variables. QRNN is chosen for its ability to handle nonlinier data distributions, whereas Hybrid LASSO-QRNN integrates the Least Absolute Shrinkage and Selection Operator (LASSO) into the Quantile Regression models to improve prediction accuracy and reduce overfitting. This study utilizes time series data from March 1, 2021, to January 24, 2025, and applies forecasting horizons of 5, 10, and 22 trading days. Based on the evaluation of QRMSE and QMAE, the hybrid LASSO-QRNN model shows improved median prediction for most stocks and horizons, especially for stocks BBCA.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | hybrid LASSO-QRNN, indikator teknikal, peramalan arah pergerakan saham perbankan, QRNN, time series, technical indicators, banking stock price forecasting. |
| Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HG Finance > HG4529 Investment analysis H Social Sciences > HG Finance > HG4910 Investments H Social Sciences > HG Finance > HG4915 Stocks--Prices |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | Rana Athaya Imtiyaz |
| Date Deposited: | 04 Aug 2025 05:00 |
| Last Modified: | 04 Aug 2025 05:00 |
| URI: | http://repository.its.ac.id/id/eprint/125480 |
Actions (login required)
 |
View Item |