Prediksi Indeks Harga Saham Gabungan (IHSG) dengan Pendekatan Machine Learning Algoritma Support Vector Machine Menggunakan Faktor Ekonomi Dosmestik dan Internasional = Support Vector Machine for Predicting Indonesia Stock Exchange Composite Index (IDX Composite) Using Domestic and International Economic Factors
Marcelinus David Wahono;
Zaafri Ananto Husodo, supervisor; Dony Abdul Chalid, examiner; Athor Subroto, examiner
(Fakultas Ekonomi dan Bisnis Universitas Indonesia, 2021)
|
|
Krisis ekonomi yang terjadi di masa lalu menimbulkan pertanyaan tentang validitasEfficient Market Hypothesis dan mendorong berkembangnya model-model yangdapat memprediksi indeks harga saham. Salah satunya yaitu prediksimemanfaatkan komponen ekonomi yang diketahui mempengaruhi IHSG danmemprosesnya dengan teknik machine learning. Support Vector Machine dikenalmemiliki kemampuan untuk menangani data berdimensi tinggi dan memilikikeunggulan dibandingkan algoritma yang lain. Performa SVM akan dibandingkandengan Artificial Neural Network (ANN) dan algoritma klasik Multiple LinearRegression (MLR). Studi ini diawali mengidentifikasi pengaruh komponenekonomi terhadap IHSG mendatang. Hasil penelitian menunjukkan bahwa SVMmemiliki kinerja paling baik dalam memprediksi harga indeks saham keesokanharinya (t + 1), namun kinerja ANN paling baik untuk memprediksi t + 5, t + 10,dst. The economic crisis that occurred in the past raised questions about the validity ofthe Efficient Market Hypothesis and encouraged the development of models thatcan predict the stock price. One of them is prediction utilizing economiccomponents known to affect IDX composite index and processed by machinelearning techniques. Support Vector Machines are known to have the ability tohandle high-dimensional data and have advantages over other algorithms. SVMperformance will be compared to Artificial Neural Networks (ANN) and the classicMultiple Linear Regression (MLR) algorithm. This study begins with identifyingthe influence of economic component on the future IDX composite index. Theresults showed that SVM had the best performance in predicting the next day stockindex prices (t+1), but ANN's performance was better than others for predictingt+5, t+10, and so on. |
 T-Marcelinus David Wahono.pdf :: Unduh
|
| No. Panggil : | T-Pdf |
| Entri utama-Nama orang : | |
| Entri tambahan-Nama orang : | |
| Entri tambahan-Nama badan : | |
| Subjek : | |
| Penerbitan : | Depok: Fakultas Ekonomi dan Bisnis Universitas Indonesia, 2021 |
| Program Studi : |
| Bahasa : | ind |
| Sumber Pengatalogan : | LibUI ind rda |
| Tipe Konten : | text |
| Tipe Media : | computer |
| Tipe Carrier : | online resource (rdacarries) |
| Deskripsi Fisik : | xiii, 76 pages : illustration ; appendix |
| Naskah Ringkas : | |
| Lembaga Pemilik : | Universitas Indonesia |
| Lokasi : | Perpustakaan UI |
| No. Panggil | No. Barkod | Ketersediaan |
|---|---|---|
| T-Pdf | 15-22-45173374 | TERSEDIA |
| Ulasan: |
| Tidak ada ulasan pada koleksi ini: 20514510 |
