Blockchain-Based Credit Scoring Model for Financial Inclusion

Thesis Abstract

Limited access to traditional credit assessment mechanisms remains a significant barrier to financial inclusion for underserved populations, particularly in developing economies where informal financial activities predominate. This study aims to design, develop, and evaluate a blockchain-based credit scoring model that leverages decentralized digital ledgers to facilitate accessible, transparent, and secure credit assessments, thereby enhancing financial inclusion. The primary objectives include analyzing the limitations of existing credit scoring systems, developing a blockchain-enabled framework that integrates alternative data sources, and empirically testing the model’s effectiveness in predicting creditworthiness among unbanked and underbanked individuals. The research adopts a mixed-methods approach comprising both qualitative and quantitative phases. The qualitative phase involves thematic analysis to explore stakeholders’ perspectives on barriers to credit access and the potential of blockchain technology in addressing these challenges. Subsequently, a quantitative research design employing a cross-sectional survey is used to empirically test the proposed model. The population consists of 3,000 residents in urban and rural areas across Nigeria, identified based on their limited or no formal banking history. Using stratified random sampling, a sample size of 600 respondents is determined to ensure representativeness and statistical power, accounting for a 95% confidence interval and a 5% margin of error. Data collection instruments include structured questionnaires targeting socio-economic data, behavioral finance indicators, and technology acceptance metrics. Additionally, interviews with banking and fintech industry experts are conducted to validate the model’s practical applicability. Instrument validity is ensured through expert review and pilot testing, with reliability assessed using Cronbach’s alpha coefficients exceeding 0.70. Quantitative data are analyzed through multiple regression analysis to examine the predictive power of the blockchain-based scoring variables, while thematic analysis of qualitative data provides contextual insights into user perceptions. The analytical framework integrates the Theory of Planned Behavior and the Diffusion of Innovation Theory, guiding the development of the credit scoring model within a blockchain architecture. The model specification employs logistic regression to identify significant predictors of creditworthiness and network analysis to evaluate the integrity of the blockchain ledger’s data validation process. Expected findings anticipate that the blockchain-based credit scoring model will demonstrate higher accuracy and transparency compared to traditional systems, especially when incorporating alternative data such as utility payments, mobile transactions, and social media activity. The findings are expected to confirm that blockchain technology enhances data integrity, reduces credit assessment costs, and fosters trust among both lenders and borrowers, thereby facilitating increased access to credit for marginalized groups. This research contributes to the existing body of knowledge by providing empirical evidence on the efficacy of blockchain technology in credit scoring and financial inclusion. It advances theoretical understanding by integrating behavioral and technological frameworks into a novel model that promotes transparency, security, and inclusivity in credit assessment processes. The study concludes that blockchain-based credit scoring models hold significant potential for transforming financial accessibility, particularly in emerging economies with limited formal credit histories. Recommendations include policy reforms to support blockchain adoption, capacity building for financial institutions, and awareness campaigns to enhance stakeholder acceptance. Future research avenues are suggested to explore the scalability of such models across different socio-economic contexts and to integrate artificial intelligence for predictive analytics, thereby further advancing digital financial services and inclusive economic growth.