Thesis Abstract

Abstract
This thesis explores the application of machine learning techniques in credit risk assessment specifically tailored for small and medium enterprises (SMEs) within the banking sector. The study addresses the challenges faced by financial institutions in accurately assessing the creditworthiness of SMEs, which are crucial for the economic growth and stability of many countries. By leveraging machine learning algorithms, this research aims to develop a more efficient and effective credit risk assessment model that can enhance decision-making processes in lending to SMEs. The thesis begins with an introduction that highlights the importance of credit risk assessment in banking, particularly for SMEs, and provides a background of the study to contextualize the research problem. The problem statement identifies the limitations of traditional credit scoring models in evaluating SMEs and emphasizes the need for more advanced and predictive methods. The objectives of the study include developing and validating a machine learning-based credit risk assessment model specifically designed for SMEs. The literature review in Chapter Two critically examines existing studies on credit risk assessment, machine learning applications in finance, and specific models used for SME credit evaluation. The review identifies gaps in the literature and provides a theoretical foundation for the research methodology. Chapter Three outlines the research methodology, including data collection methods, variables selection, model development, and evaluation techniques. It discusses the process of data preprocessing, feature engineering, model training, validation, and performance assessment to ensure the robustness and reliability of the credit risk assessment model. Chapter Four presents the findings of the study, detailing the performance of the machine learning model in predicting credit risk for SMEs. The discussion delves into the key features identified by the model, the accuracy of predictions, and the comparison with traditional credit scoring methods. The chapter also analyzes the implications of the findings for financial institutions and the potential benefits of implementing machine learning in credit risk assessment for SMEs. In the concluding Chapter Five, the thesis summarizes the key findings, implications, and contributions of the study. It reflects on the significance of the developed credit risk assessment model for SME lending practices and outlines recommendations for future research and practical applications in the banking sector. Overall, this thesis contributes to the advancement of credit risk assessment practices for SMEs through the integration of machine learning technologies. The research findings provide insights into the potential of machine learning models to enhance decision-making processes, improve risk management strategies, and promote financial inclusion for SMEs within the banking sector.

Thesis Overview

The project titled "Application of Machine Learning in Credit Risk Assessment for Small and Medium Enterprises in Banking Sector" aims to explore the utilization of machine learning techniques in enhancing credit risk assessment specifically tailored for small and medium enterprises (SMEs) within the banking sector. This research is motivated by the growing importance of SMEs in economic development and the challenges they face in accessing credit due to limitations in traditional risk assessment methods. By leveraging machine learning algorithms, this study seeks to develop a more accurate and efficient credit risk assessment model that can improve lending decisions and support the growth of SMEs. The research will begin by providing an introduction to the background of the study, highlighting the significance of the problem and setting the objectives for the investigation. The problem statement will emphasize the limitations of current credit risk assessment methods for SMEs, while the objectives will outline the specific goals of the project. The study will also acknowledge the limitations and scope of the research, providing a clear understanding of the boundaries within which the investigation will be conducted. In the literature review chapter, the research will explore existing studies and models related to credit risk assessment, machine learning applications in banking, and specifically in SME lending. This chapter will provide a comprehensive overview of the theoretical framework that underpins the study, highlighting the gaps in the current literature and identifying the key concepts that inform the development of the proposed credit risk assessment model. The research methodology chapter will outline the approach and techniques that will be employed to achieve the research objectives. This will include the data collection methods, the selection of machine learning algorithms, and the evaluation metrics that will be used to assess the performance of the credit risk assessment model. The chapter will also address any ethical considerations and potential biases that may impact the research outcomes. In the discussion of findings chapter, the research will present and analyze the results obtained from implementing the machine learning-based credit risk assessment model. The findings will be compared with traditional methods to evaluate the effectiveness and accuracy of the proposed model in predicting credit risk for SMEs. The chapter will also discuss the implications of the findings for banking institutions and SMEs, highlighting the potential benefits and challenges of adopting machine learning in credit risk assessment. Finally, the conclusion and summary chapter will provide a comprehensive overview of the research outcomes, reiterating the key findings and implications for practice. The chapter will also discuss the contributions of the study to the field of credit risk assessment and machine learning applications in banking, as well as suggest areas for future research and development in this domain.