Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Informatics and Digital Expert (INDEX) Coreid Journal
Gitarja Sandi
UIN Sunan Gunung Djati Bandung
Computer Science & IT Engineering

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparison of Long Short-Term Memory and Recurrent Neural Network For Stock Market Price Movement Classification in Islamic Bank Finance Rijki Rijki; Yana Aditia Gerhana; Gitarja Sandi; Muhammad Deden Firdaus; Eva Nurlatifah
CoreID Journal Vol. 4 No. 1 (2026): March 2026
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v4i1.152

Abstract

This study addresses the importance of accurate stock price prediction in the Islamic finance sector, where reliable forecasting supports better investment decisions and market stability. Despite the growing use of deep learning methods, comparative studies on sequential models in this domain remain limited. Therefore, this research compares the performance of Long Short-Term Memory (LSTM) and Recurrent Neural Network (RNN) models for classifying stock price movement direction of Islamic banks in Indonesia. The dataset was sourced from two Islamic banks in Indonesia, covering the period from 2022 to mid-2024, with features such as Open, High, Low, Close, Adjusted Close, and Volume. The CRISP-DM method was applied for data processing, and testing was performed with data splits of 60:40, 70:30, and 80:20, as well as epoch variations (30, 50, 80). Results indicate that RNN outperforms LSTM, with the highest accuracy of 58% for RNN and 53% for LSTM. Evaluation metrics also included precision, recall, and F1-score. In conclusion, RNN performs better for stock movement classification direction, while LSTM is more effective for minimizing prediction error.
Analisis Komparatif Algoritma One-Class Untuk Klasifikasi Teks Iklan Judi Online Berbasis Embedding IndoBERT Muhamad Randi septiansah; Cepy Slamet; Gitarja Sandi
Informatics and Digital Expert (INDEX) Vol. 7 No. 2 (2025): INDEX, November 2025
Publisher : LPPM Universitas Perjuangan Tasikmalaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36423/index.v7i2.2309

Abstract

Penyebaran iklan judi online di Indonesia terus meningkat meskipun berbagai upaya pemblokiran telah dilakukan. Iklan-iklan ini menyebar luas melalui media sosial dan situs daring, sehingga dibutuhkan sistem otomatis yang mampu menyaring konten iklan judi secara efektif. Penelitian ini mengusulkan pendekatan deteksi anomali satu kelas (one-class anomaly detection) sebagai metode penyaringan awal berbasis pembelajaran hanya dari data teks judi. Untuk merepresentasikan teks, digunakan contextual embedding IndoBERT yang menghasilkan vektor fitur berdimensi 768. Selanjutnya, dilakukan analisis komparatif terhadap tiga algoritma deteksi anomali: One-Class SVM, Isolation Forest, dan Autoencoder. Pengujian dilakukan dalam dua skenario: data seimbang dan tidak seimbang. Pada skenario seimbang, OCSVM menunjukkan performa terbaik dengan F1-score mencapai 91%. Sementara itu, dalam skenario tidak seimbang yang meniru kondisi dunia nyata, model Autoencoder mendapatkan recall terbaik mencapai 94% dengan jumlah false positive yang sangat rendah. Hasil ini menunjukkan bahwa Autoencoder layak direkomendasikan sebagai sistem penyaringan awal sebelum proses klasifikasi lanjutan atau validasi manual dilakukan.
Co-Authors Cepy Slamet Eva Nurlatifah Muhamad Randi septiansah Muhammad Deden Firdaus Rijki Rijki Yana Aditia Gerhana