Predicting Location-Based Sequential Purchasing Events by Using Spatial, Temporal, and Social Patterns

Yun Wang, Sudha Ram

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Location-based sequential event prediction is an interesting problem with many real-world applications. For example, knowing when and where people will use certain kinds of services could enable the development of robust anticipatory systems. A key to this problem is in understanding the nature of the process from which sequential data arises. Usually, human behavior exhibits distinct spatial, temporal, and social patterns. The authors examine three kinds of patterns extracted from sequential purchasing events and propose a novel model that captures contextual dependencies in spatial sequence, customers' temporal preferences, and social influence via an implicit network. Their model outperforms existing models based on evaluations using a real-world dataset of smartcard transaction records from a large educational institution with 13,753 students during a 10-month time period.

Original languageEnglish (US)
Pages (from-to)10-17
Number of pages8
JournalIEEE Intelligent Systems
Volume30
Issue number3
DOIs
StatePublished - May 1 2015

Fingerprint

Purchasing
Students

Keywords

  • artificial intelligence
  • data mining
  • human information processing
  • intelligent systems
  • network predictive analytics
  • spatial-temporal predictive analytics

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Predicting Location-Based Sequential Purchasing Events by Using Spatial, Temporal, and Social Patterns. / Wang, Yun; Ram, Sudha.

In: IEEE Intelligent Systems, Vol. 30, No. 3, 01.05.2015, p. 10-17.

Research output: Contribution to journalArticle

@article{acad5ecec801431f80ddd8b634051c5b,
title = "Predicting Location-Based Sequential Purchasing Events by Using Spatial, Temporal, and Social Patterns",
abstract = "Location-based sequential event prediction is an interesting problem with many real-world applications. For example, knowing when and where people will use certain kinds of services could enable the development of robust anticipatory systems. A key to this problem is in understanding the nature of the process from which sequential data arises. Usually, human behavior exhibits distinct spatial, temporal, and social patterns. The authors examine three kinds of patterns extracted from sequential purchasing events and propose a novel model that captures contextual dependencies in spatial sequence, customers' temporal preferences, and social influence via an implicit network. Their model outperforms existing models based on evaluations using a real-world dataset of smartcard transaction records from a large educational institution with 13,753 students during a 10-month time period.",
keywords = "artificial intelligence, data mining, human information processing, intelligent systems, network predictive analytics, spatial-temporal predictive analytics",
author = "Yun Wang and Sudha Ram",
year = "2015",
month = "5",
day = "1",
doi = "10.1109/MIS.2015.46",
language = "English (US)",
volume = "30",
pages = "10--17",
journal = "IEEE Intelligent Systems",
issn = "1541-1672",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - Predicting Location-Based Sequential Purchasing Events by Using Spatial, Temporal, and Social Patterns

AU - Wang, Yun

AU - Ram, Sudha

PY - 2015/5/1

Y1 - 2015/5/1

N2 - Location-based sequential event prediction is an interesting problem with many real-world applications. For example, knowing when and where people will use certain kinds of services could enable the development of robust anticipatory systems. A key to this problem is in understanding the nature of the process from which sequential data arises. Usually, human behavior exhibits distinct spatial, temporal, and social patterns. The authors examine three kinds of patterns extracted from sequential purchasing events and propose a novel model that captures contextual dependencies in spatial sequence, customers' temporal preferences, and social influence via an implicit network. Their model outperforms existing models based on evaluations using a real-world dataset of smartcard transaction records from a large educational institution with 13,753 students during a 10-month time period.

AB - Location-based sequential event prediction is an interesting problem with many real-world applications. For example, knowing when and where people will use certain kinds of services could enable the development of robust anticipatory systems. A key to this problem is in understanding the nature of the process from which sequential data arises. Usually, human behavior exhibits distinct spatial, temporal, and social patterns. The authors examine three kinds of patterns extracted from sequential purchasing events and propose a novel model that captures contextual dependencies in spatial sequence, customers' temporal preferences, and social influence via an implicit network. Their model outperforms existing models based on evaluations using a real-world dataset of smartcard transaction records from a large educational institution with 13,753 students during a 10-month time period.

KW - artificial intelligence

KW - data mining

KW - human information processing

KW - intelligent systems

KW - network predictive analytics

KW - spatial-temporal predictive analytics

UR - http://www.scopus.com/inward/record.url?scp=84930645550&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930645550&partnerID=8YFLogxK

U2 - 10.1109/MIS.2015.46

DO - 10.1109/MIS.2015.46

M3 - Article

VL - 30

SP - 10

EP - 17

JO - IEEE Intelligent Systems

JF - IEEE Intelligent Systems

SN - 1541-1672

IS - 3

ER -