Application of Machine Learning in Credit Risk Assessment for Small Businesses in Banking Sector

Thesis Abstract

Abstract
The banking industry plays a crucial role in the economic development of countries by offering financial services to individuals and businesses. Small businesses are a significant segment of the economy, and assessing their credit risk accurately is essential for the sustainability of banks. Traditional credit risk assessment methods have limitations in accurately predicting the creditworthiness of small businesses due to their unique characteristics and limited historical data. This thesis explores the application of machine learning techniques in credit risk assessment for small businesses in the banking sector to improve the accuracy and efficiency of credit risk evaluation. Chapter One provides an introduction to the research topic, highlighting the background, problem statement, objectives, limitations, scope, significance, structure of the thesis, and key definitions related to credit risk assessment and machine learning. Chapter Two presents a comprehensive literature review covering ten key aspects related to credit risk assessment, machine learning algorithms, small business characteristics, banking sector challenges, and previous studies on the application of machine learning in credit risk assessment. Chapter Three outlines the research methodology employed in this study, including data collection methods, selection of machine learning algorithms, feature selection techniques, model evaluation criteria, and validation procedures. It also discusses the ethical considerations and potential biases in the research process. Chapter Four presents the findings and analysis of applying machine learning algorithms to assess credit risk for small businesses in the banking sector. The chapter discusses the performance of various machine learning models in predicting credit risk, the impact of different features on credit risk assessment, and the comparison of machine learning techniques with traditional methods. Chapter Five concludes the thesis by summarizing the key findings, discussing the implications of applying machine learning in credit risk assessment for small businesses, highlighting the limitations of the study, and suggesting avenues for future research. The study contributes to the existing literature by demonstrating the potential of machine learning in enhancing credit risk assessment practices in the banking sector, particularly for small businesses, ultimately improving lending decisions and financial stability. Keywords Machine Learning, Credit Risk Assessment, Small Businesses, Banking Sector, Financial Inclusion, Predictive Modeling, Feature Selection, Model Evaluation.