Publicación: Técnicas de ciencia de datos para la modelización de la respuesta incremental en problemas de clasificación binaria
Cargando...
Fecha
2022-06-22
Autores
Editor/a
Director/a
Tutor/a
Coordinador/a
Prologuista
Revisor/a
Ilustrador/a
Derechos de acceso
Atribución-NoComercial-SinDerivadas 4.0 Internacional
info:eu-repo/semantics/openAccess
info:eu-repo/semantics/openAccess
Título de la revista
ISSN de la revista
Título del volumen
Editor
Universidad Nacional de Educación a Distancia (España). Facultad de Ciencias
Resumen
En este trabajo se estudian diferentes enfoques para la modelización de la respuesta incremental en problemas de clasificación binaria, así como los métodos para evaluarlos. Estos enfoques son útiles para definir la población a incluir en campañas de marketing directo, especialmente porque cambian el paradigma frente a modelos predictivos tradicionales y ponen el foco en los clientes persuasibles, los que se espera que respondan positivamente debido al tratamiento. Se estudia además un caso de uso en banca donde se estiman y comparan distintos modelos.
In this work, we study different approaches to model the incremental response or uplift in the binary classification problem as well as their evaluation methods. These approaches are useful to define the population to be included in a direct marketing campaign, especially since there is a paradigm change with respect to traditional predictive models: they focus on the persuadable individuals, the ones who are expected to respond positively due to the treatment. It is also studied a business case in banking where different models are estimated and compared.
In this work, we study different approaches to model the incremental response or uplift in the binary classification problem as well as their evaluation methods. These approaches are useful to define the population to be included in a direct marketing campaign, especially since there is a paradigm change with respect to traditional predictive models: they focus on the persuadable individuals, the ones who are expected to respond positively due to the treatment. It is also studied a business case in banking where different models are estimated and compared.
Descripción
Categorías UNESCO
Palabras clave
uplift modelling, true-lift modelling, net lift, prescriptive analytics, persuadable, business analytics, direct marketing, causality, literature survey
Citación
Centro
Facultad de Ciencias
Departamento
Matemáticas Fundamentales