Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Infomans: Jurnal Ilmu-ilmu Informatika dan Manajemen
Silviani, Listia
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Analisis Komparatif Model Regresi Linier dan Polinomial pada Small Dataset untuk Prediksi Timbulan Sampah: Indonesia Silviani, Listia; Firmansyah, Esa; Sutara, Beben
Infoman's : Jurnal Ilmu-ilmu Informatika dan Manajemen Vol. 19 No. 2 (2025): Infoman's
Publisher : LPPM & Fakultas Teknologi Informasi UNSAP

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Bandung Regency faces severe waste management challenges, generating an average daily volume of 1,300 tons without possessing an independent landfill facility. Consequently, accurate data-driven prediction is crucial for strategic infrastructure planning. However, the application of machine learning algorithms at the regional level is often significantly constrained by the scarcity of historical data (small datasets), which introduces high risks of overfitting and statistical bias. This study aims to evaluate prediction modeling strategies using a limited annual dataset (n=4) spanning from 2021 to 2024, sourced from Open Data Jabar. The methodology compares Linear Regression and Second-Degree Polynomial Regression algorithms by employing a full training approach combined with descriptive validation based on the Rate of Change (RoC) analysis. The results indicate that while Polynomial Regression achieves superior statistical performance with an R-squared of 0.9958 and an RMSE of 3,144.59 tons, trend analysis reveals clear signs of overfitting, as the model predicts an implausible deceleration in future waste growth that contradicts demographic realities. Conversely, Linear Regression (R2 = 0.9756) provides more stable and consistent trend estimates. Therefore, this study recommends Linear Regression as a more robust model for policy planning under limited data conditions, projecting waste generation to reach 467,964.01 tons in 2025, serving as an early warning for urgent capacity expansion.
Co-Authors Beben Sutara, Beben Firmansyah, Esa