Effective Traffic Flow Forecasting Using Taxi and Weather Data

Abstract

Short-term traffic flow forecasting is an important component of intelligent transportation systems. The forecasting results can be used to support intelligent transportation systems to plan operation and manage revenue. In this paper, we aim to predict the daily floating population by presenting a novel model using taxi trajectory data and weather information. We study the problem of floating traffic flow prediction with weather-affected New York City, and a new methodology called WTFPredict is proposed to solve this problem. In particular, we target the busiest part of the city (i.e., the airports), and identify its boundary to compute the traffic flow around the area. The experimental results based on large scale, real-life taxi and weather data (12 million records) indicate that the proposed method performs well in forecasting the short-term traffic flows. Our study will provide some valuable insights to transport management, urban planning, and location-based services (LBS).