Prediction of tariff package model using ROF-LGB algorithm

Nai Song Zheng; Xiao Wei Jiang; Yibo Ao; Xi Zhao

doi:10.1145/3352411.3352421

Prediction of tariff package model using ROF-LGB algorithm

Nai Song Zheng
, Xiao Wei Jiang
, Yibo Ao
, Xi Zhao

School of Management

Xi'an Jiaotong University
Key Lab of the Ministry of Education for Process Control and Efficiency Egineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Scopus citations

Abstract

With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus improve customer satisfaction. To address the low precision rate and data granularity of prior studies, this study combined rotation forest (ROF) and LightGBM and construct a hybrid algorithm (ROF-LGB). Grid search method was used in parameter tuning, and ten-fold cross-validation method was used to prevent overfitting. Using mobile data generated by operators, ROF-LGB method was tested and compared with other five traditional machine learning methods. The results showed that ROF-LGB method achieved better performance with better precision rate and execution efficiency in telecom tariff package recommendation.

Original language	English
Title of host publication	Proceedings of the 2019 2nd International Conference on Data Science and Information Technology, DSIT 2019
Publisher	Association for Computing Machinery
Pages	54-58
Number of pages	5
ISBN (Electronic)	9781450371414
DOIs	https://doi.org/10.1145/3352411.3352421
State	Published - 19 Jul 2019
Event	2nd International Conference on Data Science and Information Technology, DSIT 2019 - Seoul, Korea, Republic of Duration: 19 Jul 2019 → 21 Jul 2019

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	2nd International Conference on Data Science and Information Technology, DSIT 2019
Country/Territory	Korea, Republic of
City	Seoul
Period	19/07/19 → 21/07/19

Keywords

LightGBM
Prediction
ROF-LGB
Tariff package

Access to Document

10.1145/3352411.3352421

Cite this

@inproceedings{293096d7157c46ef9cdd4abe9e4520c0,

title = "Prediction of tariff package model using ROF-LGB algorithm",

abstract = "With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus improve customer satisfaction. To address the low precision rate and data granularity of prior studies, this study combined rotation forest (ROF) and LightGBM and construct a hybrid algorithm (ROF-LGB). Grid search method was used in parameter tuning, and ten-fold cross-validation method was used to prevent overfitting. Using mobile data generated by operators, ROF-LGB method was tested and compared with other five traditional machine learning methods. The results showed that ROF-LGB method achieved better performance with better precision rate and execution efficiency in telecom tariff package recommendation.",

keywords = "LightGBM, Prediction, ROF-LGB, Tariff package",

author = "Zheng, \{Nai Song\} and Jiang, \{Xiao Wei\} and Yibo Ao and Xi Zhao",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computing Machinery.; 2nd International Conference on Data Science and Information Technology, DSIT 2019 ; Conference date: 19-07-2019 Through 21-07-2019",

year = "2019",

month = jul,

day = "19",

doi = "10.1145/3352411.3352421",

language = "英语",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "54--58",

booktitle = "Proceedings of the 2019 2nd International Conference on Data Science and Information Technology, DSIT 2019",

}

Zheng, NS, Jiang, XW, Ao, Y & Zhao, X 2019, Prediction of tariff package model using ROF-LGB algorithm. in Proceedings of the 2019 2nd International Conference on Data Science and Information Technology, DSIT 2019. ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 54-58, 2nd International Conference on Data Science and Information Technology, DSIT 2019, Seoul, Korea, Republic of, 19/07/19. https://doi.org/10.1145/3352411.3352421

Prediction of tariff package model using ROF-LGB algorithm. / Zheng, Nai Song; Jiang, Xiao Wei; Ao, Yibo et al.
Proceedings of the 2019 2nd International Conference on Data Science and Information Technology, DSIT 2019. Association for Computing Machinery, 2019. p. 54-58 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Prediction of tariff package model using ROF-LGB algorithm

AU - Zheng, Nai Song

AU - Jiang, Xiao Wei

AU - Ao, Yibo

AU - Zhao, Xi

PY - 2019/7/19

Y1 - 2019/7/19

N2 - With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus improve customer satisfaction. To address the low precision rate and data granularity of prior studies, this study combined rotation forest (ROF) and LightGBM and construct a hybrid algorithm (ROF-LGB). Grid search method was used in parameter tuning, and ten-fold cross-validation method was used to prevent overfitting. Using mobile data generated by operators, ROF-LGB method was tested and compared with other five traditional machine learning methods. The results showed that ROF-LGB method achieved better performance with better precision rate and execution efficiency in telecom tariff package recommendation.

AB - With the slowing growth of the telecommunication market and the intense competition for existing customers, Customer Churn Management has become a crucial task for all mobile network operators. Recommendation models based on customer behaviors are widely used by operators to provide diverse telecom tariff packages for suitable people and thus improve customer satisfaction. To address the low precision rate and data granularity of prior studies, this study combined rotation forest (ROF) and LightGBM and construct a hybrid algorithm (ROF-LGB). Grid search method was used in parameter tuning, and ten-fold cross-validation method was used to prevent overfitting. Using mobile data generated by operators, ROF-LGB method was tested and compared with other five traditional machine learning methods. The results showed that ROF-LGB method achieved better performance with better precision rate and execution efficiency in telecom tariff package recommendation.

KW - LightGBM

KW - Prediction

KW - ROF-LGB

KW - Tariff package

UR - https://www.scopus.com/pages/publications/85072812219

U2 - 10.1145/3352411.3352421

DO - 10.1145/3352411.3352421

M3 - 会议稿件

AN - SCOPUS:85072812219

T3 - ACM International Conference Proceeding Series

SP - 54

EP - 58

BT - Proceedings of the 2019 2nd International Conference on Data Science and Information Technology, DSIT 2019

PB - Association for Computing Machinery

T2 - 2nd International Conference on Data Science and Information Technology, DSIT 2019

Y2 - 19 July 2019 through 21 July 2019

ER -

Prediction of tariff package model using ROF-LGB algorithm

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this