Publicação
Unlocking Marketing Insights Through the Analysis of Credit Card Complaints
| Resumo: | Fintech companies have been challenging traditional financial institutions with the use of technology. Traditional institutions have long and trustful relationships with their clients, but fintechs offer ease of use, speed, and personalization. More recently, the participation of Buy Now Pay Later (BNPL) in the credit market share grew, affecting both types of companies. More and more clients are leaving their credit cards aside and opting for this type of credit. In this context, it is crucial to understand what the user’s perceptions of fintech and traditional institutions are. This study makes use of Text Mining to investigate the similarities, differences, and temporal changes that can lead to insights that support product development, design of better customer experience, and communication strategy. As a case to test the methodology it was used the complaint database from the Consumer Financial Protection Bureau (CFPB). To uncover insights, sentiment analysis, topic modeling, and word co-occurrence analysis were employed. The analysis showed that predominant complaints across both fintech and traditional institutions include "communication" and "account management," highlighting shared challenges. However, distinct issues like "credit reporting" and "disputes" emerge for fintechs and "fraud" for traditional institutions, underscoring the importance of addressing these concerns for reputation and revenue management. Temporal analysis reveals persistent challenges in "communication" and "account management" for both types of organizations, with fluctuations in other topics such as "transactions," "fraud," and "customer service" over time. This research demonstrates that Text Mining techniques effectively analyze usergenerated content (UGC) across various fields, uncovering critical user pain points and enabling businesses to address customer complaints and improve products and communication strategies. By prioritizing processes that boost satisfaction, firms can enhance their value and gain insights for competitor analysis. |
|---|---|
| Autores principais: | Guimarães, Yramaia de Paula Salviano |
| Assunto: | Fintech Text Mining UGC Financial sector LDA CFPB Product Development SDG 12 - Responsible production and consumption |
| Ano: | 2024 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso embargado |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | Fintech companies have been challenging traditional financial institutions with the use of technology. Traditional institutions have long and trustful relationships with their clients, but fintechs offer ease of use, speed, and personalization. More recently, the participation of Buy Now Pay Later (BNPL) in the credit market share grew, affecting both types of companies. More and more clients are leaving their credit cards aside and opting for this type of credit. In this context, it is crucial to understand what the user’s perceptions of fintech and traditional institutions are. This study makes use of Text Mining to investigate the similarities, differences, and temporal changes that can lead to insights that support product development, design of better customer experience, and communication strategy. As a case to test the methodology it was used the complaint database from the Consumer Financial Protection Bureau (CFPB). To uncover insights, sentiment analysis, topic modeling, and word co-occurrence analysis were employed. The analysis showed that predominant complaints across both fintech and traditional institutions include "communication" and "account management," highlighting shared challenges. However, distinct issues like "credit reporting" and "disputes" emerge for fintechs and "fraud" for traditional institutions, underscoring the importance of addressing these concerns for reputation and revenue management. Temporal analysis reveals persistent challenges in "communication" and "account management" for both types of organizations, with fluctuations in other topics such as "transactions," "fraud," and "customer service" over time. This research demonstrates that Text Mining techniques effectively analyze usergenerated content (UGC) across various fields, uncovering critical user pain points and enabling businesses to address customer complaints and improve products and communication strategies. By prioritizing processes that boost satisfaction, firms can enhance their value and gain insights for competitor analysis. |
|---|