对比三种模型在噪声数据下的计价预测表现，给出城市出行系统建模建议。
Robust Taxi Fare Prediction Under Noisy Conditions: A Comparative Study of GAT, TimesNet, and XGBoost
- 用图注意力网络、时序网络和梯度提升树比较噪声环境下的计价预测能力
- 在超5500万条真实数据上验证，模型对数据质量敏感度差异显著
- 适合交通平台研发人员参考，尤其关注鲁棒性与数据预处理策略
精确的计价预测对网约车平台和城市出行系统至关重要。本研究基于包含超过5500万条记录的真实数据集，评估三种机器学习模型——图注意力网络（GAT）、XGBoost和TimesNet——在出租车费用预测中的表现。同时分析原始（含噪）与去噪版本数据，考察数据质量对模型性能的影响。研究从预测准确性、校准度、不确定性估计、分布外（OOD）鲁棒性及特征敏感性等多个维度进行评估，并探索了KNN插补、高斯噪声注入和基于自编码器的去噪等预处理策略。结果揭示了经典模型与深度学习模型在真实场景下的关键差异，为构建稳健、可扩展的城市计价预测系统提供了实用指导。
原文摘要 · Abstract (English)
Precise fare prediction is crucial in ride-hailing platforms and urban mobility systems. This study examines three machine learning models-Graph Attention Networks (GAT), XGBoost, and TimesNet to evaluate their predictive capabilities for taxi fares using a real-world dataset comprising over 55 million records. Both raw (noisy) and denoised versions of the dataset are analyzed to assess the impact of data quality on model performance. The study evaluated the models along multiple axes, including predictive accuracy, calibration, uncertainty estimation, out-of-distribution (OOD) robustness, and feature sensitivity. We also explore pre-processing strategies, including KNN imputation, Gaussian noise injection, and autoencoder-based denoising. The study reveals critical differences between classical and deep learning models under realistic conditions, offering practical guidelines for building robust and scalable models in urban fare prediction systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。