A carregar...
Publicação
Optimizing Credit Portfolio Management Through Advanced Data Analytics
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.53 MB | Adobe PDF |
Autores
Orientador(es)
Resumo(s)
Credit portfolio management is critical in helping financial institutions grow profitability and
stay competitive. As access to customer data increases and market dynamics evolve, there is
growing pressure to use advanced analytics to better understand client behavior and make
smarter credit decisions. This thesis introduces an analytical framework that combines
behavioral clustering techniques with predictive modeling to enhance client segmentation
and credit offer targeting. Despite the abundance of available data, many institutions still rely
on generalized marketing approaches, often missing key opportunities for portfolio growth.
To address these gaps, the proposed framework links clustering insights with supervised
learning models to predict loan acceptance propensity more precisely. The approach
emphasizes robust data preparation, thoughtful feature engineering, and rigorous model
validation to deliver operationally useful results. Ultimately, the research aims to support
more effective marketing, stronger client engagement, and sustainable portfolio growth
through smarter analytics. The findings offer a scalable foundation for advancing credit
portfolio management through more data-driven, client-centric practices.
Descrição
Dissertation presented as the partial requirement for obtaining a Master's degree in Data Science and Advanced Analytics, specialization in Business Analytics
Palavras-chave
Credit portfolio management predictive modeling customer segmentation clustering algorithms behavioral analytics SDG 8 - Decent work and economic growth SDG 10 - Reduced inequalities