PERBANDINGAN MODEL LSTM DAN GRU PADA PREDIKSI HARGA SAHAM ANTAM DENGAN TEKNIK FEATURE ENGINEERING

Syafiz Amiero Wisesanadar, . (2025) PERBANDINGAN MODEL LSTM DAN GRU PADA PREDIKSI HARGA SAHAM ANTAM DENGAN TEKNIK FEATURE ENGINEERING. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

	Text ABSTRAK.pdf Download (128kB)
	Text AWAL.pdf Download (1MB)
	Text BAB 1.pdf Restricted to Repository UPNVJ Only Download (157kB)
	Text BAB 2.pdf Restricted to Repository UPNVJ Only Download (1MB)
	Text BAB 3.pdf Restricted to Repository UPNVJ Only Download (1MB)
	Text BAB 4.pdf Restricted to Repository UPNVJ Only Download (563kB)
	Text BAB 5.pdf Download (131kB)
	Text DAFTAR PUSTAKA.pdf Download (156kB)
	Text RIWAYAT HIDUP.pdf Restricted to Repository UPNVJ Only Download (81kB)
	Text LAMPIRAN.pdf Restricted to Repository UPNVJ Only Download (112kB)
	Text HASIL PLAGIARISME.pdf Restricted to Repository staff only Download (9MB)
	Text ARTIKEL KI.pdf Restricted to Repository staff only Download (864kB)

Abstract

Stock price prediction faces complex challenges due to data that cannot be predicted linearly and exhibits High volatility that is difficult to capture using conventional methods. This study aims to compare the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models in predicting PT Aneka Tambang Tbk (ANTAM) stock prices by implementing feature engineering techniques. The research methodology utilizes ANTAM historical stock data from May 2015-2025 consisting of 2,483 observations with the addition of seven derived features (High_Low, Open_Close, HL_PCT, OC_PCT, Volume_Change, Return, Volatility). Both models were built with identical two-layer architecture (64 and 32 units) using 5-fold TimeSeriesSplit validation and evaluation with MAE, RMSE, MAPE, and R² metrics. Results show GRU outperformed LSTM with MAE 0.0037, RMSE 0.0057, MAPE 2.78%, R² 0.9588, while LSTM recorded MAE 0.0041, RMSE 0.0099, MAPE 3.08%, R² 0.9455, with both models meeting standard evaluation criteria without overfitting.

Item Type:	Thesis (Skripsi)
Additional Information:	[No.Panggil: 1810511044] [Pembimbing: Neny Rosmawarni] [Penguji 1: Widya Cholil] [Penguji 2: Novi Trisman Hadi]
Uncontrolled Keywords:	deep learning, feature engineering, GRU, LSTM, Stock Price Prediction
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software
Divisions:	Fakultas Ilmu Komputer > Program Studi Informatika (S1)
Depositing User:	SYAFIZ AMIERO WISESANADAR
Date Deposited:	05 Aug 2025 08:21
Last Modified:	05 Aug 2025 08:21
URI:	http://repository.upnvj.ac.id/id/eprint/37816

Actions (login required)

View Item