Modeling Tenant’s Credit Scoring Using Logistic Regression

This study implements the multivariable logistic regression to develop a credit scoring model based on tenants’ characteristics. The history of tenant is not considered. Rental information tenants was collected from landlord company in Malaysia. Parameters were estimated by using penalized maximum likelihood estimation with ridge since separation training data detected. initial factors considered that affect score their gender, age, marital status, monthly income, household expense-to-income ratio, number dependents, previous rent, and months late payment. However, status factor then excluded due its low significance model. Meanwhile, tenant’s generated calculating probability defaulting. main are payment, age. There no underfitting or overfitting proposed which means model’s bias variance low.