부산대학교 도서관

In recent years, the transactions of second hand cars have increased due to the Corona Virus Disease 2019 (COVID-19) epidemic, supply chain disruption and other factors. The number and amount of auto loans are increasing, and the number and amount of defaults are also increasing. For auto lenders, if they can find out the factors affecting auto loan defaults or manage these risk factors in the credit granting process to reduce loan defaults, many losses can be avoided. Numerous algorithms and frameworks have been proposed by scholars to solve credit scoring problems in the past. Only a few studies have examined the factors affecting second car loan default. However, this issue is of great importance to the auto loan industry. Therefore, this study intends to define a hybrid multi-criteria decision making (MCDM) model to mine the database of defaulting customers of loans of second hand cars. First, this study introduces the Dominance Based Rough Set Approach (DRSA) to analyze the characteristics of the defaulting clients, derive the core attributes as well as the decision rules. Then, the Formal Concept Analysis (FCA) is adopted to derive the main concepts affecting the default of auto loans. After that, the Decision Making Trial and Evaluation Laboratory (DEMATEL) based Analytic Network Process, or the DANP, is used to derive the influence relationships among the core attributes and the weights associated with these attributes. The empirical results can be used as a reference for auto loan companies. Based on the database of one of major financial institutions in Taiwan, the feasibility of the analytic framework was verified. According to the mining results of the customer database, age, gender, marital status, education, income and loan amount are the core attributes, and 15 decision rules including 'If those customers who own college degree or above and borrow more than 1.5 million dollars, then the customer will default' are derived. In addition, the record of violation, loan amount and income are the main factors affecting the default. The results of this study can be used as a basis for future loan verification by financial institutions, as well as for the introduction of intelligent automatic loan verification mechanism and the development of intelligent vehicle loan platform.