• JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
  • JoomlaWorks Simple Image Rotator
 
  Bookmark and Share
 
 
Master's Dissertation
DOI
https://doi.org/10.11606/D.55.2024.tde-21032024-084138
Document
Author
Full name
Vitor Wilgner Buzinaro
Institute/School/College
Knowledge Area
Date of Defense
Published
São Carlos, 2024
Supervisor
Committee
Perdoná, Gleici da Silva Castro (President)
Caldarelli, Carlos Eduardo
Conceição, Katiane Silva
Zuanetti, Daiane Aparecida
Title in Portuguese
Fidelização e Retenção de Clientes em Modelos de Negócios Não Contratuais: Estimando a Probabilidade de Churn
Keywords in Portuguese
Análise de sobrevivência
Classificação de churn
Negócios não contratuais
Transformação digital
Abstract in Portuguese
A transformação digital no varejo tem causado uma mudança profunda na forma como as empresas conduzem seus negócios, com a integração de tecnologias avançadas, como análise de dados e inteligência artificial, impactando a interação com os clientes. O e-commerce expandiu as fronteiras do varejo, oferecendo conveniência e acesso a uma variedade maior de produtos. A transformação digital tornou-se uma necessidade para empresas que desejam permanecer competitivas e atender às crescentes demandas dos consumidores por uma experiência de compra eficiente e personalizada. Dentro desse contexto, identificar a saúde do cliente ao longo de seu ciclo de vida é essencial, uma vez que a desistência pode ocorrer de forma imprevisível. O modelo BG/NBD (Beta- geometric Negative Binomial Distribution) foi usado para prever a probabilidade de churn (desistência) dos clientes, com resultados significativos e boa capacidade preditiva. A análise de Kaplan-Meier foi usada para examinar o comportamento de compra e informações demográficas, destacando que clientes com cestas de produtos maiores tendem a permanecer mais tempo, enquanto aqueles com compras de alto valor têm relacionamentos menos duradouros. Em resumo, o modelo BG/NBD foi eficaz na classificação de clientes ativos e inativos, e a análise de Kaplan-Meier forneceu informações valiosas sobre retenção e fidelização de clientes, capacitando a empresa a tomar decisões estratégicas com recursos da transformação digital.
Title in English
Customer Loyalty and Retention in Non-Contractual Business Models: Estimating Churn Probability
Keywords in English
Churn classification
Digital transformation
Non contractual business settings
Survival analysis
Abstract in English
The digital transformation in retail has caused a profound change in how companies conduct their businesses, with the integration of advanced technologies such as data analysis and artificial intelligence impacting customer interactions. E-commerce has expanded the boundaries of retail, offering convenience and access to a wider range of products. Digital transformation has become a necessity for companies that want to remain competitive and meet the growing demands of consumers for an efficient and personalized shopping experience. Within this context, identifying the customers health throughout their lifecycle is essential, as churn can occur unpredictably. The BG/NBD model was used to predict the probability of customer churn, with significant results and good predictive capability. Kaplan-Meier analysis was used to examine purchasing behavior and demographic information, high- lighting that customers with larger product baskets tend to stay longer, while those with high-value purchases have shorter-lasting relationships. In summary, the BG/NBD model was effective in classifying active and inactive customers, and Kaplan-Meier analysis provided valuable information on customer retention and loyalty, empowering the company to make data-driven strategic decisions based on digital transformation capabilities.
 
WARNING - Viewing this document is conditioned on your acceptance of the following terms of use:
This document is only for private use for research and teaching activities. Reproduction for commercial use is forbidden. This rights cover the whole data about this document as well as its contents. Any uses or copies of this document in whole or in part must include the author's name.
Publishing Date
2024-03-21
 
WARNING: Learn what derived works are clicking here.
All rights of the thesis/dissertation are from the authors
CeTI-SC/STI
Digital Library of Theses and Dissertations of USP. Copyright © 2001-2024. All rights reserved.