Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach

By Jintao Ke, Hongyu Zheng, Hai Yang, Xiqun Michael Chen. arXiv.org, 2017

660 citations recorded by the source corpus.

Abstract Short-term passenger demand forecasting is of great importance to the on-demand ride service platform, which can incentivize vacant cars moving from over-supply regions to over-demand regions. The spatial dependencies, temporal dependencies, and exogenous dependencies need to be considered simultaneously, however, which makes short-term passenger demand forecasting challenging. We propose a novel deep learning (DL) approach, named the fusion convolutional long short-term memory network (FCL-Net), to address these three dependencies within one end-to-end learning architecture. The model is stacked and fused by multiple convolutional long short-term memory (LSTM) layers, standard LSTM layers, and convolutional layers. The fusion of convolutional techniques and the LSTM network enables the proposed DL approach to better capture the spatio-temporal characteristics and correlations of explanatory variables. A tailored spatially aggregated random forest is employed to rank the importance of the explanatory variables. The ranking is then used for feature selection. The proposed DL approach is applied to the short-term forecasting of passenger demand under an on-demand ride service platform in Hangzhou, China. The experimental results, validated on the real-world data provided by DiDi Chuxing, show that the FCL-Net achieves the better predictive performance than traditional approaches including both classical time-series prediction models and state-of-art machine learning algorithms (e.g., artificial neural network, XGBoost, LSTM and CNN). Furthermore, the consideration of exogenous variables in addition to the passenger demand itself, such as the travel time rate, time-of-day, day-of-week, and weather conditions, is proven to be promising, since they reduce the root mean squared error (RMSE) by 48.3%. It is also interesting to find that the feature selection reduces 24.4% in the training time and leads to only the 1.8% loss in the forecasting accuracy measured by RMSE in the proposed model. This paper is one of the first DL studies to forecast the short-term passenger demand of an on-demand ride service platform by examining the spatio-temporal correlations.

Subfields: Building and Construction, Transportation

View Paper: https://www.semanticscholar.org/paper/2937ffeef1918988485040cad447d4fc9d0462a4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Transportation

Citations in the corpus

STG2Seq: Spatial-temporal Graph to Sequence Model for Multi-step Passenger Demand Forecasting (2019, methodology): “…methods: 4) DeepST [ Zhang et al. , 2016a ] ; 5) ResST-Net [ Zhang et al. , 2017 ] ; 6) DMVST-Net [ Yao et al. , 2018 ] ; 7) ConvLSTM [ Xingjian et al. , 2015 ] ; 8) FCL-Net [ Ke et al. , 2017 ] ; 9) FlowFlexDP [ Chu et al. , 2018 ] ; 10)DCRNN [ Li et al. , 2018 ] ; 11) STGCN [ Yu et al. , 2018 ] .”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “They evaluated their framework using three real datasets and by comparing against HA, ordinary linear regression (OLR), XGBoost [52], DeepST [53], ResST-Net [54], DMVST-Net [55], ConvLSTM [56], FCL-Net [57], FlowFlexDP [58], DCRNN [6], and STGCN [27].”
Forward Modeling for Partial Observation Strategy Games - A StarCraft Defogger (2018, background): “[9] propose a LSTM with convolutional instead of linear interactions and demonstrate good performance on predicting percipitation based on radar echo images; [10] use a similar approach to forecast passenger demand for on-demand ride services; [11] estimate future traffic in Bejing based on image re”
Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting (2019, methodology): “There are rich amount of works on this topic, including predicting bike ﬂows (Zhang, Zheng, and Qi 2017), the taxi demand (Ke et al. 2017b; Yao et al. 2018b), the arrival time (Li et al. 2018b), and the precipitation (Shi et al. 2015; 2017), where the prediction is aggregated in rectangular…”
Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting (2020, methodology): “To extract spatial patterns, some methods [4, 2, 34, 12, 35, 36, 37, 15] ﬁrst model trafﬁc ﬂows as multi-channel matrices representation, then employ deep convolution neural networks to learn hierarchical of features.”
Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting (2020, methodology): “…recently, CNNs and graph neural networks (GNNs) have become the most widely used models in detecting patterns thanks to their progress in capturing spatial and topological dependencies in images, videos, and graphs (Ke, Zheng, Yang, & Chen, 2017; Li et al., 2017; Wu et al., 2018; Yu et al., 2017).”
Task-Agnostic Dynamics Priors for Deep Reinforcement Learning (2019, methodology): “Our frame prediction model is closest in spirit to the ConvolutionalLSTM model which has been applied to several domains (Xingjian et al., 2015; Zhu et al., 2017; Ke et al., 2017).”
T-GCN: A Temporal Graph Convolutional Network for Traffic Prediction (2018, methodology): “Ke et al. [43] proposed a new deep learning method called the fusion convolutional long short-term memory network (FCL-Net), taking into account spatial dependence, temporal dependence, and exogenous dependence for short-term passenger demand forecasting.”
Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks (2019, neutral): “video-analysis tasks such as anomaly detection [62], sequence prediction [63], and passenger-demand prediction [64], [65].”
Deep Learning for Intelligent Transportation Systems: A Survey of Emerging Trends (2020, background): “[50] explore extensions of the convolutional-LSTM architecture [104] to model short-term demand forecasting, and demonstrate how multiple convolutional-LSTM blocks can be leveraged to incorporate spatio-temporal features from”
Predicting Station-level Hourly Demands in a Large-scale Bike-sharing Network: A Graph Convolutional Neural Network Approach (2017, background): “The computation process of the LSTM cell follows standard steps involving the input gate, forget gate, output gate and memory cell state; details can be found in previous studies (Ke et al., 2017; Ma et al., 2015).”
Deep Learning for Spatio-Temporal Data Mining: A Survey (2019, methodology): “ConvLSTM [1], [89], [152], [186], [142], [66], [189], [63], [138] AE/SDAE [106], [185], [13] [49], [158], [95] [31], [16], [179], [44], [46], [170] RBM/DBN [108] [127] [131], [51], [59] Seq2Seq [75], [161], [20], [162] [82], [81] Hybrid [155], [133], [99] [87], [52] [177], [29], [19], [6], [163], [1”
Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction (2018, background): “Recently, several studies use convolutional LSTM (Shi et al. 2015) to handle spatial and temporal dependency for taxi demand prediction (Ke et al. 2017; Zhou et al. 2018).”
Deep Learning on Traffic Prediction: Methods, Analysis, and Future Directions (2021, neutral): “CNN – [109] RNN [72], [110]–[112] RNN+Attention [80]”
Dynamic pricing and matching in ride‐hailing platforms (2019, background): “Short-term demand forecasting is needed for a variety of large-scale transportation applications, ranging from ride-hailing, taxi (Ke et al. 2017, Yao et al. 2018), and ambulance services (Zhou et al. 2015).”