Saved in:
Bibliographic Details
Main Authors: Rahman, M. H., Rifaat, S. M., Sadeek, S. N., Abrar, M., Wang, D.
Format: Preprint
Published: 2020
Subjects:
Online Access:https://arxiv.org/abs/2012.15408
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912016472473600
author Rahman, M. H.
Rifaat, S. M.
Sadeek, S. N.
Abrar, M.
Wang, D.
author_facet Rahman, M. H.
Rifaat, S. M.
Sadeek, S. N.
Abrar, M.
Wang, D.
contents Ride-hailing system requires efficient management of dynamic demand and supply to ensure optimal service delivery, pricing strategies, and operational efficiency. Designing spatio-temporal forecasting models separately in a task-wise and city-wise manner to forecast demand and supply-demand gap in a ride-hailing system poses a burden for the expanding transportation network companies. Therefore, a multi-task learning architecture is proposed in this study by developing gated ensemble of spatio-temporal mixture of experts network (GESME-Net) with convolutional recurrent neural network (CRNN), convolutional neural network (CNN), and recurrent neural network (RNN) for simultaneously forecasting these spatio-temporal tasks in a city as well as across different cities. Furthermore, a task adaptation layer is integrated with the architecture for learning joint representation in multi-task learning and revealing the contribution of the input features utilized in prediction. The proposed architecture is tested with data from Didi Chuxing for: (i) simultaneously forecasting demand and supply-demand gap in Beijing, and (ii) simultaneously forecasting demand across Chengdu and Xian. In both scenarios, models from our proposed architecture outperformed the single-task and multi-task deep learning benchmarks and ensemble-based machine learning algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2012_15408
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Gated Ensemble of Spatio-temporal Mixture of Experts for Multi-task Learning in Ride-hailing System
Rahman, M. H.
Rifaat, S. M.
Sadeek, S. N.
Abrar, M.
Wang, D.
Machine Learning
Ride-hailing system requires efficient management of dynamic demand and supply to ensure optimal service delivery, pricing strategies, and operational efficiency. Designing spatio-temporal forecasting models separately in a task-wise and city-wise manner to forecast demand and supply-demand gap in a ride-hailing system poses a burden for the expanding transportation network companies. Therefore, a multi-task learning architecture is proposed in this study by developing gated ensemble of spatio-temporal mixture of experts network (GESME-Net) with convolutional recurrent neural network (CRNN), convolutional neural network (CNN), and recurrent neural network (RNN) for simultaneously forecasting these spatio-temporal tasks in a city as well as across different cities. Furthermore, a task adaptation layer is integrated with the architecture for learning joint representation in multi-task learning and revealing the contribution of the input features utilized in prediction. The proposed architecture is tested with data from Didi Chuxing for: (i) simultaneously forecasting demand and supply-demand gap in Beijing, and (ii) simultaneously forecasting demand across Chengdu and Xian. In both scenarios, models from our proposed architecture outperformed the single-task and multi-task deep learning benchmarks and ensemble-based machine learning algorithms.
title Gated Ensemble of Spatio-temporal Mixture of Experts for Multi-task Learning in Ride-hailing System
topic Machine Learning
url https://arxiv.org/abs/2012.15408