Widya Puteri Aulia
UIN Sunan Gunung Djati Bandung

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

Found 2 Documents
Search

Analysis of Feature Engineering on LSTM and GRU Forecasting Performance Across Food Commodities with Different Volatility Levels Zalid Qomalita Hijriana; Muhammad Mulyawan; Lina Alfaridah ZH; Widya Puteri Aulia
CoreID Journal Vol. 4 No. 2 (2026): July 2026
Publisher : CV. Generasi Intelektual Digital

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60005/coreid.v4i2.182

Abstract

Food commodity price prediction plays a crucial role in monitoring food price stability and inflation, particularly for commodities with varying volatility characteristics. This study compares the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models in forecasting daily food commodity prices in Bandung City, using chili and rice dataset. Daily price data were collected and modeled in two experimental scenarios: forecasting using only historical price data and forecasting with temporal feature engineering. The results showed that GRU consistently outperformed LSTM across all experiments. Without feature engineering, GRU achieved a MAPE score 0.49% and 3.26% for rice and chili, respectively. The incorporation of temporal features improved forecasting performance, reducing forecasting errors by up to 31.30% for rice and 29.55% for chili. The best overall performance was achieved by the GRU model with temporal feature engineering (MAPE rice = 0.48% and MAPE chili = 2.48%). These findings indicate that incorporating feature engineering remains beneficial for enhancing deep learning models performance. This study contributes to the development of deep learning methods for food commodity price forecasting and provides an understanding of the role of temporal feature engineering in handling commodities with different levels of volatility.
Comparative Analysis of District PPID Website Accessibility in West Java Using Public Information Disclosure Scores Gita Cahyani Lestari; Aldy Rialdy Atmadja; Widya Puteri Aulia; Lina Alfaridah. ZH
Jurnal Accounting Information System (AIMS) Vol. 9 No. 2 (2026)
Publisher : Ma'soem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/aims.v9i2.2248

Abstract

Public information disclosure and web accessibility are important aspects of Electronic-Based Government Systems (SPBE). This study aims to evaluate and compare the accessibility of six regency-level Information and Documentation Management Officer (PPID) websites in West Java based on their 2025 Public Information Disclosure Monitoring and Evaluation (Monev KIP) scores. Using extreme group sampling, the websites were divided into high-performer (Sumedang, Karawang, and Bandung) and low-performer (Cianjur, Indramayu, and Sukabumi) groups. The websites were automatically tested based on the Web Content Accessibility Guidelines (WCAG) 2.2 using PowerMapper and AudioEye. The results showed 114 findings from AudioEye and 28 findings from PowerMapper, consisting of 22 WCAG issues and 6 ARIA warnings. The high-performer group had more findings than the low-performer group, with 62 AudioEye findings and 18 PowerMapper findings, compared with 52 and 10 findings, respectively. Common accessibility problems included missing accessible names for links and images, low color contrast, and unclear focus indicators. These results indicate that high public information disclosure scores do not always indicate better web accessibility. The findings also highlight the need to combine automated and manual testing for a more complete accessibility evaluation.