Robust Taxi Fare Prediction Under Noisy Conditions: A Comparative Study of GAT, TimesNet, and XGBoost

2025/07/26 by P. N. Krishna Moorthy, Moorthy, Padmavathi
Engineering · Social Sciences · #62H30 (Secondary) #62M10 (Primary) #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Human Mobility and Location-Based Analysis #I.2.10 #I.2.6 #I.5.1 #Machine Learning (cs.LG) #Traffic Prediction and Management Techniques #Transportation and Mobility Innovations

paper · pdf · doi:10.48550/arxiv.2507.20008

openalex publication_date 2025/07/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Can bin-wise scaling improve consistency and adaptivity of prediction uncertainty for machine learning regression ?
• Energy-based Out-of-Distribution Detection for Graph Neural Networks
• FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
• Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
• Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift
• Graph Attention Networks
• Semi-Supervised Classification with Graph Convolutional Networks

Related

• Fairness-enhancing deep learning for ride-hailing demand prediction
• Artificial Neural Networks Applied to Taxi Destination Prediction
• STEF-DHNet: Spatiotemporal External Factors Based Deep Hybrid Network for Enhanced Long-Term Taxi Demand Prediction
• One Model Fits All: Cross-Region Taxi-Demand Forecasting
• On Designing Day Ahead and Same Day Ridership Level Prediction Models for City-Scale Transit Networks Using Noisy APC Data