Widyaningrum, Erlyne Nadhilah (2023) Optimasi Paramater Suppport Vector Regression Berbasis Firefly Algorithm Dan Genetic Algorithm Untuk Peramalan Harga Saham Sektor Konstruksi Dan Bangunan. Masters thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 6003211027-Master_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
6003211027-Master_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (2MB) | Request a copy |
Abstract
Saham sangat didukung oleh pemerintahan dan telah disahkan undang-undang mengenai penyelenggaraan kegiatan di bidang pasar modal. Dengan menyertakan modal atau investasi saham maka investor memiliki klaim atas aset dan pendapatan
suatu perusahaan. Harga saham bergerak secara fluktuatif dan cenderung dinamis setiap waktu sehingga diperlukan prediksi harga saham untuk memaksimalkan keuntungan bagi para investor dan menghindari kerugian akibat dari sifat harga saham. Data penutupan harga saham dapat digunakan model SVR (Support Vector Regression) yang menawarkan solusi global optimal yang bekerja dengan memetakan data ke ruang berdimensi tinggi dan memiliki performansi yang baik dalam mengatasi permasalahan time series. Namun, untuk mendapatkan hasil dari SVR yang optimal diperlukan pemilihan nilai parameter secara hati hati atau dilakukan optimasi agar tidak didapatkan nilai local optimum sehingga dalam penelitian ini digunakan metode optimasi genetic algorithm dan firefly algorithm dalam pemilihan parameter SVR agar diperoleh hasil ramalan yang lebih baik.
Kedua algoritma tersebut dibandingkan dengan SVR grid search berdasarkan nilai akurasinya dengan menggunakan sMAPE serta berdasarkan computational time nya. Hasil pemodelan menunjukkan bahwa model ARX-SVR dengan X adalah outlier memberikan hasil ramalan pada data out-sample terbaik untuk studi kasus peramalan harga penutupan saham ADHI dan PTPP. Model terbaik yang terbentuk adalah model SVR dengan optimasi firefly algorithm. Model ini memberikan hasil peramalan dengan sMAPE untuk harga penutupan saham ADHI adalah 1.349386% dan sMAPE untuk harga penutupan saham PTPP adalah 1.49705%.
=======================================================================================================================================
Stock is strongly supported by the government and have been passed by law regarding the implementation of activities in the capital market sector. By including capital or stock investment, investors have a claim on the assets and income of a company. Stock prices fluctuate and tend to be dynamic over time, so stock price predictions are needed to maximize profits for investors and avoid losses due to the nature of stock prices. Stock price closing data are generally non-linear, so the SVR (Support Vector Regression) model is used which offers an optimal global solution that works by mapping data to high-dimensional space and has good performance
in overcoming time series and non-linear data problems. However, to obtain optimal SVR results, careful selection of parameter values is required, or optimization is carried out so that local optimum values are not obtained, so that
in this study the genetic algorithm and firefly algorithm optimization methods were used in the selection of SVR parameters in order to obtain better forecast results.
The two algorithms will be compared with SVR grid search based on their accuracy values, namely sMAPE and based on their computational time. The modeling results show that the ARX-SVR model with X is an outlier gives forecast results on
the best out-sample data for the case study forecasting the closing price of ADHI and PTPP stocks. The best model formed is SVR with firefly algorithm optimization.
This model provides forecasting results with sMAPE for the closing price of ADHI's shares of 1.349386% and sMAPE for the closing price of PTPP's shares is 1.49705%.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | firefly algorithm, genetic algorithm, optimasi, support vector regression, firefly algorithm, genetic algorithm, optimization, support vector regression |
| Subjects: | Q Science > Q Science (General) > Q325.5 Machine learning. Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry) Q Science > QA Mathematics > QA402.5 Genetic algorithms. Q Science > QA Mathematics > QA9.58 Algorithms |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | Erlyne Nadhilah Widyaningrum |
| Date Deposited: | 08 Aug 2023 01:13 |
| Last Modified: | 08 Aug 2023 01:13 |
| URI: | http://repository.its.ac.id/id/eprint/103862 |
Actions (login required)
 |
View Item |