Collaborative analytics for predicting expressway-traffic congestion

There are many ways to build a predictive model from data. Besides the numerous classification or regression algorithms to choose from, there are countless possibilities of useful data transformation prior to modeling. To assist in discovering good predictive analytics workflows, we introduced recen...

Full description

Saved in:
Bibliographic Details
Main Authors: Chong, Chee Seng, Zoebir, Bon, Tan, Alan Yu Shyang, Tjhi, William-Chandra, Zhang, Tianyou, Lee, Kee Khoon, Li, Reuben Mingguang, Tung, Whye Loon, Lee, Francis Bu-Sung
Other Authors: School of Computer Engineering
Format: Conference or Workshop Item
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/98045
http://hdl.handle.net/10220/12269
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-98045
record_format dspace
spelling sg-ntu-dr.10356-980452020-05-28T07:17:22Z Collaborative analytics for predicting expressway-traffic congestion Chong, Chee Seng Zoebir, Bon Tan, Alan Yu Shyang Tjhi, William-Chandra Zhang, Tianyou Lee, Kee Khoon Li, Reuben Mingguang Tung, Whye Loon Lee, Francis Bu-Sung School of Computer Engineering Annual International Conference on Electronic Commerce (14th : 2012) DRNTU::Engineering::Computer science and engineering There are many ways to build a predictive model from data. Besides the numerous classification or regression algorithms to choose from, there are countless possibilities of useful data transformation prior to modeling. To assist in discovering good predictive analytics workflows, we introduced recently a collaborative analytics system that allows workflow sharing and reuse. We designed a recommendation engine for the system to enable matching of analytics needs with relevant workflows stored in repository. The engine relies on meta-predictive modeling of traffic-analysis workflow-characteristics. In this paper, we present a feasibility study of applying this collaborative analytics system to predict traffic congestion. Different ways to build predictive models from traffic dataset are pooled as shared workflows. We demonstrate that through dynamic recommendation of workflows that are suitable for the real-time varying traffic data, a reliable congestion prediction can be achieved. The promising results showcase that systematic collaboration among data scientists made possible by our system can be a powerful tool to produce very accurate prediction from data. 2013-07-25T07:29:02Z 2019-12-06T19:49:59Z 2013-07-25T07:29:02Z 2019-12-06T19:49:59Z 2012 2012 Conference Paper Chong, C. S., Zoebir, B., Tan, A. Y. S., Tjhi, W.-C., Zhang, T., Lee, K. K., et al. (2012). Collaborative analytics for predicting expressway-traffic congestion. Proceedings of the 14th Annual International Conference on Electronic Commerce. https://hdl.handle.net/10356/98045 http://hdl.handle.net/10220/12269 10.1145/2346536.2346542 en © 2012 ACM.
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Chong, Chee Seng
Zoebir, Bon
Tan, Alan Yu Shyang
Tjhi, William-Chandra
Zhang, Tianyou
Lee, Kee Khoon
Li, Reuben Mingguang
Tung, Whye Loon
Lee, Francis Bu-Sung
Collaborative analytics for predicting expressway-traffic congestion
description There are many ways to build a predictive model from data. Besides the numerous classification or regression algorithms to choose from, there are countless possibilities of useful data transformation prior to modeling. To assist in discovering good predictive analytics workflows, we introduced recently a collaborative analytics system that allows workflow sharing and reuse. We designed a recommendation engine for the system to enable matching of analytics needs with relevant workflows stored in repository. The engine relies on meta-predictive modeling of traffic-analysis workflow-characteristics. In this paper, we present a feasibility study of applying this collaborative analytics system to predict traffic congestion. Different ways to build predictive models from traffic dataset are pooled as shared workflows. We demonstrate that through dynamic recommendation of workflows that are suitable for the real-time varying traffic data, a reliable congestion prediction can be achieved. The promising results showcase that systematic collaboration among data scientists made possible by our system can be a powerful tool to produce very accurate prediction from data.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Chong, Chee Seng
Zoebir, Bon
Tan, Alan Yu Shyang
Tjhi, William-Chandra
Zhang, Tianyou
Lee, Kee Khoon
Li, Reuben Mingguang
Tung, Whye Loon
Lee, Francis Bu-Sung
format Conference or Workshop Item
author Chong, Chee Seng
Zoebir, Bon
Tan, Alan Yu Shyang
Tjhi, William-Chandra
Zhang, Tianyou
Lee, Kee Khoon
Li, Reuben Mingguang
Tung, Whye Loon
Lee, Francis Bu-Sung
author_sort Chong, Chee Seng
title Collaborative analytics for predicting expressway-traffic congestion
title_short Collaborative analytics for predicting expressway-traffic congestion
title_full Collaborative analytics for predicting expressway-traffic congestion
title_fullStr Collaborative analytics for predicting expressway-traffic congestion
title_full_unstemmed Collaborative analytics for predicting expressway-traffic congestion
title_sort collaborative analytics for predicting expressway-traffic congestion
publishDate 2013
url https://hdl.handle.net/10356/98045
http://hdl.handle.net/10220/12269
_version_ 1681057956212244480