Machine learning framework estimates pedestrian volumes using GIS data

Researchers have developed a machine learning framework to estimate pedestrian volumes using GIS data, aiming to improve safety investment prioritization for transportation agencies. The proposed pipeline, which includes feature selection and gradient boosting models, demonstrated a 12% reduction in cross-validated RMSE compared to the traditional Negative Binomial GLM. The best-performing model, a histogram-based gradient boosting model with Poisson loss and L1 Lasso feature selection, also achieved a 19% reduction in holdout RMSE. The associated code has been made available on GitHub. AI

IMPACT This framework could improve urban planning and safety by providing more accurate pedestrian traffic estimates.

RANK_REASON Academic paper detailing a new machine learning framework for a specific application. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• alphaXiv
• arXiv
• arXivLabs
• CatalyzeX
• DagsHub
• GitHub
• Gotit.pub
• Hugging Face
• IArxiv
• Influence Flower
• Negative Binomial GLM
• Oregon
• Portland
• ScienceCast

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →