Enhancing Credit Risk Evaluation in Automotive Finance: A Machine Learning Approach

Credit risk assessment is important for auto finance companies to reduce financial losses, defaults, and repossessions while promoting market stability. Traditional credit scoring models that rely on limited data have struggled to accurately predict the probability of default. This capstone project explores and focuses on the use of advanced machine learning techniques to improve credit risk assessment by leveraging large datasets and algorithmic complexity. This capstone project focuses on developing a machine learning model to predict consumer default in the automotive finance industry using Volvo Financial Services credit data. The project aims to identify important determinants of credit risk and evaluate how machine learning systems work well to predict the probability of defaults. The study begins with a comprehensive exploratory data analysis, which includes various financial indicators such as net worth, working capital, and revenue. This analysis helps in understanding the distribution of the target variable and identifying outliers that could affect the risk assessment mode This analysis helps in understanding the distribution of the target variable and identifying outliers that could affect the risk assessment model. The project follows a methodological approach that includes data preprocessing to address missing values and outliers and feature engineering to enhance the predictive power of financial key indicators in credit risk. The research work aims to improve the accuracy and efficiency of credit risk assessment by adopting machine learning models that can incorporate real-time data and capture non-linear relationships. This would help automotive finance companies predict and manage credit risk more effectively, thereby drastically reducing defaults and repossessions. Overall, this abstract highlights the process and expected outcomes of the study, with emphasis on the potential of machine learning to transform risk assessment practices in automotive finance.