- -

A combination of multi-period training data and ensemble methods to improve churn classification of housing loan customers

RiuNet: Institutional repository of the Polithecnic University of Valencia

Share/Send to

Cited by

Statistics

  • Estadisticas de Uso

A combination of multi-period training data and ensemble methods to improve churn classification of housing loan customers

Show simple item record

Files in this item

dc.contributor.author Seppälä, Tomi es_ES
dc.contributor.author Thuy, Le es_ES
dc.date.accessioned 2018-11-07T08:31:05Z
dc.date.available 2018-11-07T08:31:05Z
dc.date.issued 2018-09-07
dc.identifier.isbn 9788490486894
dc.identifier.uri http://hdl.handle.net/10251/112049
dc.description.abstract [EN] Customer retention has been the focus of customer relationship management in the financial sector during the past decade. The first and important step in customer retention is to classify the customers into possible churners, those likely to switch to another service provider, and non-churners. The second step is to take action to retain the most probable churners. The main challenge in churn classification is the rarity of churn events. In order to overcome this, two aspects are found to improve the churn classification model: the training data and the algorithm. The recently proposed multi-period training data approach is found to outperform the single period training data thanks to the more effective use of longitudinal data. Regarding the churn classification algorithms, the most advanced and widely employed is the ensemble method, which combines multiple models to produce a more powerful one. Two popularly used ensemble techniques, random forest and gradient boosting, are found to outperform logistic regression and decision tree in classifying churners from non-churners. The study uses data of housing loan customers from a Nordic bank. The key finding is that models combining the multi-period training data approach with ensemble methods performs the best. es_ES
dc.format.extent 4 es_ES
dc.language Inglés es_ES
dc.publisher Editorial Universitat Politècnica de València es_ES
dc.relation.ispartof 2nd International Conference on Advanced Reserach Methods and Analytics (CARMA 2018) es_ES
dc.rights Reconocimiento - No comercial - Sin obra derivada (by-nc-nd) es_ES
dc.subject Web data es_ES
dc.subject Internet data es_ES
dc.subject Big data es_ES
dc.subject QCA es_ES
dc.subject PLS es_ES
dc.subject SEM es_ES
dc.subject Conference es_ES
dc.subject Churn prediction es_ES
dc.subject Ensemble methods es_ES
dc.subject Random forest es_ES
dc.subject Gradient boosting es_ES
dc.subject Multiple period training data es_ES
dc.subject Housing loan churn es_ES
dc.title A combination of multi-period training data and ensemble methods to improve churn classification of housing loan customers es_ES
dc.type Capítulo de libro es_ES
dc.type Comunicación en congreso es_ES
dc.identifier.doi 10.4995/CARMA2018.2018.8334
dc.rights.accessRights Abierto es_ES
dc.description.bibliographicCitation Seppälä, T.; Thuy, L. (2018). A combination of multi-period training data and ensemble methods to improve churn classification of housing loan customers. En 2nd International Conference on Advanced Reserach Methods and Analytics (CARMA 2018). Editorial Universitat Politècnica de València. 141-144. https://doi.org/10.4995/CARMA2018.2018.8334 es_ES
dc.description.accrualMethod OCS es_ES
dc.relation.conferencename CARMA 2018 - 2nd International Conference on Advanced Research Methods and Analytics es_ES
dc.relation.conferencedate Julio 12-13,2018 es_ES
dc.relation.conferenceplace Valencia, Spain es_ES
dc.relation.publisherversion http://ocs.editorial.upv.es/index.php/CARMA/CARMA2018/paper/view/8334 es_ES
dc.description.upvformatpinicio 141 es_ES
dc.description.upvformatpfin 144 es_ES
dc.type.version info:eu-repo/semantics/publishedVersion es_ES
dc.relation.pasarela OCS\8334 es_ES


This item appears in the following Collection(s)

Show simple item record