A hazard based approach to user return time prediction

Komal Kapoor, Mingxuan Sun, Jaideep Srivastava, Tao Ye

Research output: Chapter in Book/Report/Conference proceedingConference contribution

27 Citations (Scopus)

Abstract

In the competitive environment of the internet, retaining and growing one's user base is of major concern to most web services. Furthermore, the economic model of many web services is allowing free access to most content, and generating revenue through advertising. This unique model requires securing user time on a site rather than the purchase of good which makes it crucially important to create new kinds of metrics and solutions for growth and retention efforts for web services. In this work, we address this problem by proposing a new retention metric for web services by concentrating on the rate of user return. We further apply predictive analysis to the proposed retention metric on a service, as a means for characterizing lost customers. Finally, we set up a simple yet effective framework to evaluate a multitude of factors that contribute to user return. Specifically, we define the problem of return time prediction for free web services. Our solution is based on the Cox's proportional hazard model from survival analysis. The hazard based approach offers several benefits including the ability to work with censored data, to model the dynamics in user return rates, and to easily incorporate different types of covariates in the model. We compare the performance of our hazard based model in predicting the user return time and in categorizing users into buckets based on their predicted return time, against several baseline regression and classification methods and find the hazard based approach to be superior.

Original languageEnglish
Title of host publicationProceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
PublisherAssociation for Computing Machinery
Pages1719-1728
Number of pages10
ISBN (Print)9781450329569
DOIs
Publication statusPublished - 2014
Externally publishedYes
Event20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014 - New York, NY
Duration: 24 Aug 201427 Aug 2014

Other

Other20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014
CityNew York, NY
Period24/8/1427/8/14

Fingerprint

Hazards
Web services
Marketing
Internet
Economics

Keywords

  • customer relationship management
  • growth and retention
  • hazard based methods
  • online user behavior

ASJC Scopus subject areas

  • Software
  • Information Systems

Cite this

Kapoor, K., Sun, M., Srivastava, J., & Ye, T. (2014). A hazard based approach to user return time prediction. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1719-1728). Association for Computing Machinery. https://doi.org/10.1145/2623330.2623348

A hazard based approach to user return time prediction. / Kapoor, Komal; Sun, Mingxuan; Srivastava, Jaideep; Ye, Tao.

Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2014. p. 1719-1728.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kapoor, K, Sun, M, Srivastava, J & Ye, T 2014, A hazard based approach to user return time prediction. in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, pp. 1719-1728, 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2014, New York, NY, 24/8/14. https://doi.org/10.1145/2623330.2623348
Kapoor K, Sun M, Srivastava J, Ye T. A hazard based approach to user return time prediction. In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery. 2014. p. 1719-1728 https://doi.org/10.1145/2623330.2623348
Kapoor, Komal ; Sun, Mingxuan ; Srivastava, Jaideep ; Ye, Tao. / A hazard based approach to user return time prediction. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery, 2014. pp. 1719-1728
@inproceedings{9540f3f27a0f48bab92bbac028b768e9,
title = "A hazard based approach to user return time prediction",
abstract = "In the competitive environment of the internet, retaining and growing one's user base is of major concern to most web services. Furthermore, the economic model of many web services is allowing free access to most content, and generating revenue through advertising. This unique model requires securing user time on a site rather than the purchase of good which makes it crucially important to create new kinds of metrics and solutions for growth and retention efforts for web services. In this work, we address this problem by proposing a new retention metric for web services by concentrating on the rate of user return. We further apply predictive analysis to the proposed retention metric on a service, as a means for characterizing lost customers. Finally, we set up a simple yet effective framework to evaluate a multitude of factors that contribute to user return. Specifically, we define the problem of return time prediction for free web services. Our solution is based on the Cox's proportional hazard model from survival analysis. The hazard based approach offers several benefits including the ability to work with censored data, to model the dynamics in user return rates, and to easily incorporate different types of covariates in the model. We compare the performance of our hazard based model in predicting the user return time and in categorizing users into buckets based on their predicted return time, against several baseline regression and classification methods and find the hazard based approach to be superior.",
keywords = "customer relationship management, growth and retention, hazard based methods, online user behavior",
author = "Komal Kapoor and Mingxuan Sun and Jaideep Srivastava and Tao Ye",
year = "2014",
doi = "10.1145/2623330.2623348",
language = "English",
isbn = "9781450329569",
pages = "1719--1728",
booktitle = "Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining",
publisher = "Association for Computing Machinery",

}

TY - GEN

T1 - A hazard based approach to user return time prediction

AU - Kapoor, Komal

AU - Sun, Mingxuan

AU - Srivastava, Jaideep

AU - Ye, Tao

PY - 2014

Y1 - 2014

N2 - In the competitive environment of the internet, retaining and growing one's user base is of major concern to most web services. Furthermore, the economic model of many web services is allowing free access to most content, and generating revenue through advertising. This unique model requires securing user time on a site rather than the purchase of good which makes it crucially important to create new kinds of metrics and solutions for growth and retention efforts for web services. In this work, we address this problem by proposing a new retention metric for web services by concentrating on the rate of user return. We further apply predictive analysis to the proposed retention metric on a service, as a means for characterizing lost customers. Finally, we set up a simple yet effective framework to evaluate a multitude of factors that contribute to user return. Specifically, we define the problem of return time prediction for free web services. Our solution is based on the Cox's proportional hazard model from survival analysis. The hazard based approach offers several benefits including the ability to work with censored data, to model the dynamics in user return rates, and to easily incorporate different types of covariates in the model. We compare the performance of our hazard based model in predicting the user return time and in categorizing users into buckets based on their predicted return time, against several baseline regression and classification methods and find the hazard based approach to be superior.

AB - In the competitive environment of the internet, retaining and growing one's user base is of major concern to most web services. Furthermore, the economic model of many web services is allowing free access to most content, and generating revenue through advertising. This unique model requires securing user time on a site rather than the purchase of good which makes it crucially important to create new kinds of metrics and solutions for growth and retention efforts for web services. In this work, we address this problem by proposing a new retention metric for web services by concentrating on the rate of user return. We further apply predictive analysis to the proposed retention metric on a service, as a means for characterizing lost customers. Finally, we set up a simple yet effective framework to evaluate a multitude of factors that contribute to user return. Specifically, we define the problem of return time prediction for free web services. Our solution is based on the Cox's proportional hazard model from survival analysis. The hazard based approach offers several benefits including the ability to work with censored data, to model the dynamics in user return rates, and to easily incorporate different types of covariates in the model. We compare the performance of our hazard based model in predicting the user return time and in categorizing users into buckets based on their predicted return time, against several baseline regression and classification methods and find the hazard based approach to be superior.

KW - customer relationship management

KW - growth and retention

KW - hazard based methods

KW - online user behavior

UR - http://www.scopus.com/inward/record.url?scp=84907027138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84907027138&partnerID=8YFLogxK

U2 - 10.1145/2623330.2623348

DO - 10.1145/2623330.2623348

M3 - Conference contribution

AN - SCOPUS:84907027138

SN - 9781450329569

SP - 1719

EP - 1728

BT - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

PB - Association for Computing Machinery

ER -