Claim Missing Document
Check
Articles

Found 2 Documents
Search

Xgboost Modeling To Predicting Land Use-Based Trip Generation: Literature Review Tony Kristiawan; Leksmono Suryo Putranto; Haris Muhammadun
JURNAL TEKNIK SIPIL CENDEKIA (JTSC) Vol 7 No 4 (2026): October
Publisher : Departement of Civil Engineering, Universitas Winaya Mukti

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51988/jtsc.v7i4.733

Abstract

Reliable trip generation prediction is essential for transportation planning, traffic forecasting, and sustainable urban development. However, conventional statistical models may struggle to capture nonlinear relationships between land-use characteristics and travel demand. This study systematically reviews research published between 2019 and 2025 on XGBoost applications in land-use-based trip generation and related travel-demand prediction. A total of 25 studies were analyzed based on data characteristics, land-use and built-environment variables, modeling approaches, validation techniques, evaluation metrics, and research findings. The review indicates that XGBoost can capture complex nonlinear relationships and interactions among explanatory variables, making it a promising approach for modeling travel patterns. However, predictive performance varies across datasets, geographical contexts, target variables, and evaluation methods, limiting direct comparisons among studies. Key challenges include model interpretability, data quality and availability, spatial transferability, and integration with Geographic Information Systems (GIS) and real-time transportation data. This review synthesizes methodological developments, identifies limitations in the existing evidence, and highlights opportunities for improving model explainability, validation, and cross-context generalization. The findings provide a basis for developing more reliable and context-sensitive trip generation models to support evidence-based transportation planning and smart city applications.
Visitor Attraction Model of Trade and Service Facilities at the Business Unit Level in the Planned Government Centre Area of Serang Regency Tony Kristiawan; Leksmono Suryo Putranto; Haris Muhammadun
Jurnal Geosains West Science Vol 4 No 03 (2023): Jurnal Geosains West Science
Publisher : Westscience Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/jgws.v4i03.3984

Abstract

Estimating the traffic impact of the planned Serang Regency Government Centre requires attraction models for every constituent land use, including the trade and service facilities that dominate the Serang-Jakarta arterial corridor. This study develops a visitor attraction model from 138 business units across nine activity types in Ciruas and Kragilan Districts, using daily visitor counts as the dependent variable and three independent variables: parking area, building area, and number of employees. The analysis works at the business unit level, unlike the common practice of aggregating to village level, which reduces the sample to 27 observations. All three independent variables correlate positively and significantly with the dependent variable, at 0.875 for parking area, 0.730 for building area, and 0.552 for employees. Multiple regression yields a coefficient of determination of 0.836, yet the employee coefficient turns negative and significant (B = -28.182; p < 0.001). Adding business type controls raises the coefficient of determination to 0.862 without restoring the sign, and logarithmic transformation of all three predictors merely relocates the reversal. The linear specification also fails the Breusch-Pagan test (LM = 847.2; p < 0.001) and is dominated by 14 market units whose removal lowers the slope by 78 percent. The elasticity model ln Y = 2.068 + 0.501 ln X, with X the parking area, is the only specification satisfying every criterion, with a coefficient of determination of 0.372 and Breusch-Pagan p = 0.320. The elasticity of 0.501 implies diminishing returns: doubling parking area raises visitor numbers by about 41 percent