Reizha Fajrian, . (2025) PREDIKSI HARGA SAHAM BANK BCA MENGGUNAKAN ALGORITMA PATCHTST DAN OPTIMASI STRATEGI TRADING DENGAN PPO. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.
![[img]](http://repository.upnvj.ac.id/style/images/fileicons/text.png) |
Text
ABSTRAK.pdf Download (111kB) |
|
Text
AWAL.pdf Restricted to Repository UPNVJ Only Download (668kB) |
|
Text
BAB 1.pdf Restricted to Repository UPNVJ Only Download (116kB) |
|
Text
BAB 2.pdf Restricted to Repository UPNVJ Only Download (192kB) |
|
Text
BAB 3.pdf Restricted to Repository UPNVJ Only Download (633kB) |
|
Text
BAB 4.pdf Restricted to Repository UPNVJ Only Download (259kB) |
|
Text
BAB 5.pdf Download (112kB) |
|
Text
DAFTAR PUSTAKA.pdf Download (139kB) |
|
Text
RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (126kB) |
|
Text
HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (11MB) |
|
Text
ARTIKEL KI.pdf Restricted to Repository staff only Download (166kB) |
Abstract
Stock price prediction is a major challenge in the financial world due to market volatility and non-linear characteristics. In this research, a deep learning-based approach using Patch Time Series Transformer (PatchTST) is employed to predict BBCA (PT Bank Central Asia Tbk) stock prices in the short term. PatchTST utilizes a Transformer architecture specifically modified for time series data, processing input in patch format to enhance the model's ability to capture long-term patterns. The prediction results from PatchTST are used as input for a trading agent trained using the Proximal Policy Optimization (PPO) reinforcement learning algorithm, aiming to optimize adaptive decision-making strategies for selling, buying, or holding stocks. Evaluation is conducted by comparing the PPO-derived strategy with conventional strategies such as Buy & Hold and SMA Crossover. Results show that the combination of PatchTST and PPO produces higher cumulative returns, lower portfolio drawdown, and better Sharpe Ratio and Profit Factor.
| Item Type: | Thesis (Skripsi) |
|---|---|
| Additional Information: | [No.Panggil: 1810511078] [Pembimbing: Dr. Widya Cholil, M.I.T] [Penguji 1: Ati Zaidiah, S.Kom.,M.TI] [Penguji 2: Radinal Setyadinsa, S.Pd., M.T.I] |
| Uncontrolled Keywords: | Stock prediction, PatchTST, PPO, reinforcement learning, deep learning |
| Subjects: | L Education > L Education (General) Q Science > Q Science (General) T Technology > T Technology (General) |
| Divisions: | Fakultas Ilmu Komputer > Program Studi Informatika (S1) |
| Depositing User: | REIZHA FAJRIAN |
| Date Deposited: | 06 Aug 2025 04:47 |
| Last Modified: | 06 Aug 2025 04:47 |
| URI: | http://repository.upnvj.ac.id/id/eprint/37881 |
Actions (login required)
 |
View Item |