Come with me now: New potential consumers identification from competitors

Hugo Alatrista-Salas, Miguel Nunez-del-Prado, Victoria Zevallos

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

The telecommunications industry is confronted more and more to aggressive marketing campaigns from competitor carriers. Therefore, they need to improve the subscriber targeting to propose more attractive offers for gaining new subscribers. In the present effort, a five steps methodology to find new potential subscribers using supervised learning techniques over imbalanced datasets is proposed. The proposed technique applies community detection to infers consumption information of competitors carriers subscribers within the communities. Besides, it uses a sampling technique to reduce the effect of a dominant class for an imbalanced classification task. The proposal is evaluated with a real dataset from a Peruvian carrier. The dataset contains one-month data, which is about 200 millions of transaction. The results show that the proposed technique is able to identify between two to ten times more new potential clients, depending on the sampling technique, as shows using the top decile lift value.
Original languageEnglish
Title of host publicationInformation management and dig data
Subtitle of host publication6th International Conference, SIMBig 2019, Proceedings
EditorsJuan Antonio Lossio-Ventura, Nelly Condori-Fernandez, Jorge Carlos Valverde-Rebaza
Place of PublicationCham
PublisherSpringer
Pages252-266
Number of pages15
ISBN (Electronic)978-3-030-46140-9
ISBN (Print)978-3-030-46139-3
DOIs
StatePublished - 23 Apr 2020
EventInternational Conference on Information Management and Big Data - Lima, Peru
Duration: 21 Aug 201923 Aug 2019
Conference number: 6th
https://simbig.org/SIMBig2019/

Publication series

NameCommunications in Computer and Information Science
Volume1070 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceInternational Conference on Information Management and Big Data
Abbreviated titleSIMBig 2019
Country/TerritoryPeru
CityLima
Period21/08/1923/08/19
Internet address

Bibliographical note

Publisher Copyright:
© Springer Nature Switzerland AG 2020.

Keywords

  • Community detection
  • Imbalanced classification
  • Subscribers attraction

Fingerprint

Dive into the research topics of 'Come with me now: New potential consumers identification from competitors'. Together they form a unique fingerprint.

Cite this