Taxi Demand Prediction with LSTM-Based Combination Model

Abstract

Taxi demands to predict in urban city helps to guide the drivers to cruise and pickup riders, which increases drivers' income and decreases riders' waiting time. The taxi demands prediction problem is usually cast as a time series prediction task, and deep models such as recurrent neural network (RNN) or long short-term memory (LSTM) is adopted for the prediction. In this paper, we present a LSTM-based combination model to predict taxi demand based on the recent demand and other relevant information. More specifically, we use a spatio-temporal component to capture the spatio-temporal information and use an attribute component to obtain external information (e.g. weather, point of interest), and these two components are combined to make the final predictions. We evaluate our method of two real-world datasets, and the results show that the proposed approach outperforms other prediction methods.