Puspita, Adinda Puja (2025) Perbandingan Peramalan Harga Saham Sektor Teknologi Menggunakan Support Vector Regression Dengan Optimasi Genetic Algorithm dan Particle Swarm Optimization. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 5006211048_Undergraduate Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
5006211048_Undergraduate Thesis.pdf - Accepted Version Restricted to Repository staff only Download (8MB) | Request a copy |
Abstract
Teknologi telah menjadi bagian penting dalam kehidupan modern, terutama setelah pandemi COVID-19 yang mempercepat transformasi digital. Sektor teknologi di Indonesia menunjukkan perkembangan pesat, salah satunya tercermin dari indeks saham IDXTECHNO yang berisi saham perusahaan teknologi terdaftar di Bursa Efek Indonesia. Namun, volatilitas harga saham sektor ini menjadi tantangan bagi investor, sehingga diperlukan metode peramalan yang mampu menangkap pola data secara efektif, baik linier maupun nonlinier. Penelitian ini bertujuan untuk membandingkan metode peramalan harga saham pada sektor teknologi menggunakan Support Vector Regression (SVR), Genetic Algorithm-Support Vector Regression (GA-SVR), dan Particle Swarm Optimization-Support Vector Regression (PSO-SVR). Time lag yang signifikan pada model ARIMA akan digunakan sebagai input pada model SVR. Metode GA dan PSO diintegrasikan ke dalam SVR untuk mengoptimalkan parameter model, sehingga diharapkan dapat meningkatkan akurasi peramalan. Hasil penelitian diperoleh bahwa dari 11 data saham perusahaan diperoleh hasil terbaik adalah metode GA-SVR di mana metode ini menempati urutan pertama 10 perusahaan berdasarkan nilai akurasi yang dihitung dengan MAPE. Penelitian ini diharapkan digunakan sebagai acuan dalam mitigasi risiko investasi, di mana investor dan pihak terkait dapat mengambil keputusan investasi yang lebih terinformasi untuk meminimalkan potensi kerugian akibat fluktuasi harga saham, khususnya di sektor teknologi.
=====================================================================================================================================
Technology has become an essential part of modern life, especially after the COVID-19 pandemic that accelerated digital transformation. The technology sector in Indonesia shows rapid development, one of which is reflected in the IDXTECHNO stock index which contains stocks of technology companies listed on the Indonesia Stock Exchange. However, the volatility of this sector's stock prices is a challenge for investors, so a forecasting method is needed that is able to capture data patterns effectively, both linear and nonlinear. This study aims to compare stock price forecasting methods in the technology sector using Support Vector Regression (SVR), Genetic Algorithm-Support Vector Regression (GA-SVR), and Particle Swarm Optimization-Support Vector Regression (PSO-SVR). Significant time lags in the ARIMA model will be used as input to the SVR model. GA and PSO methods are integrated into SVR to optimize model parameters, so it is expected to improve forecasting accuracy. The results showed that from 11 company stock data, the best result is the GA-SVR method where this method ranks the first 10 companies based on the accuracy value calculated by MAPE. This research is expected to be used as a reference in investment risk mitigation, where investors and related parties can make more informed investment decisions to minimize potential losses due to stock price fluctuations, especially in the technology sector.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | ARIMA, Genetic Algorithm, Particle Swarm Optimization, Peramalan Harga Saham, Support Vector Regression, Optimization Stock Price Forecasting |
| Subjects: | H Social Sciences > HG Finance H Social Sciences > HG Finance > HG4915 Stocks--Prices |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis |
| Depositing User: | Adinda Puja Puspita |
| Date Deposited: | 31 Jul 2025 02:53 |
| Last Modified: | 31 Jul 2025 02:53 |
| URI: | http://repository.its.ac.id/id/eprint/124799 |
Actions (login required)
 |
View Item |