摘 要：本文针对网约公交出行需求预测问题，提出一种基于ARIMA模型的预测方法。通过整合乘客出行数据、天气数据和时间特征数据，构建了综合特征的时间序列预测模型。研究结果表明，考虑天气温度和时间特征的ARIMA模型较基础ARIMA模型具有更好的预测精度，能够为网约公交的运营调度提供科学依据。本研究为城市微循环交通系统的智能化提供了理论和实践参考。
关键词：ARIMA模型；网约公交；出行需求预测
中图分类号：U491.1+2；O211.61 文献标志码：A DOI：10.15917/j.cnki.1006-3331.2025.04.006
Research on Travel Demand Forecasting of Ride-hailing Bus Based on ARIMA
YI Kunyan, LI Xiang, XIONG Gang, WEN Jianfeng
Abstract: This paper aims at the problem of travel demand forecasting for ride-hailing buses and proposes a prediction method based on the ARIMA model.It constructs a time series prediction model with comprehensive features by integrating passenger travel data,weather data,and time feature data.The research results show that the ARIMA model,which considers weather temperature and time characteristics,has better prediction accuracy than the basic ARIMA traditional model and can provide a scientific basis for the operation and scheduling of ride-hailing buses.This study provides theoretical and practical references for the intelligence of urban micro circulation transportation systems.
Key words: ARIMA model; ride-hailing bus; travel demand forecast
