Thesis Abstract

Abstract
This thesis explores the application of machine learning techniques in credit risk assessment for small businesses in developing countries. The study focuses on addressing the challenges faced by financial institutions in accurately evaluating the creditworthiness of small businesses, particularly in regions with limited historical credit data and high levels of economic volatility. By leveraging the power of machine learning algorithms, this research aims to enhance the accuracy and efficiency of credit risk assessment processes, ultimately facilitating increased access to finance for small businesses in developing countries. The research begins with a comprehensive review of the existing literature on credit risk assessment, machine learning applications in finance, and the specific challenges faced by small businesses in developing countries. Through a detailed analysis of ten key studies, the literature review highlights the potential benefits and limitations of using machine learning models for credit risk assessment in this context. Subsequently, the research methodology section outlines the approach taken to design and conduct the study. The methodology includes data collection strategies, model selection criteria, feature engineering techniques, and model evaluation methods. By incorporating both quantitative and qualitative analysis approaches, the research aims to provide a holistic understanding of the impact of machine learning on credit risk assessment for small businesses in developing countries. The findings section presents a detailed discussion of the results obtained from applying machine learning algorithms to credit risk assessment data. The analysis includes the performance evaluation of various machine learning models, the identification of key risk factors for small businesses, and the comparison of traditional credit scoring methods with machine learning-based approaches. The findings shed light on the effectiveness of machine learning in improving credit risk assessment accuracy and reducing default rates for small businesses in developing countries. In conclusion, this thesis summarizes the key insights gained from the study and offers recommendations for financial institutions, policymakers, and researchers interested in enhancing credit risk assessment processes for small businesses in developing countries. The research contributes to the growing body of knowledge on the application of machine learning in finance and underscores the importance of leveraging advanced technologies to promote financial inclusion and economic growth in underserved markets.

Thesis Overview