Credit Scoring

Credit Scoring Model for Motorcycle Financing: A Preliminary Analysis

Abstract

This article presents a preliminary analysis of a credit scoring model developed to assess the payment behaviour of borrowers in the motorcycle financing industry. The study focuses on identifying significant predictors of payment completion and evaluating the model's effectiveness. Data from a sample of borrowers were analysed using logistic regression and significance testing. The results show that age, number of dependents, downpayment to unit price ratio, and income to balance ratio are significant indicators of credit status and payment behaviour. However, the model's performance needs further validation and improvement through larger sample sizes. The credit scoring system is considered relevant, but complementary to other strategies for the company.

I. Introduction

The motorcycle financing industry plays a vital role in providing access to affordable transportation for many individuals. Financial institutions need to manage credit risk and predict borrowers' payment behaviour. To address these issues, a credit scoring model was developed to identify factors that influence borrowers' payment behaviour and assess their creditworthiness. This article presents the preliminary findings of the study.

II. Methodology

Data from a sample of borrowers were collected and analysed. Descriptive statistics were used to present the characteristics of the borrowers and the units sold. The logistic regression was employed to identify significant predictors of payment behaviour, while the significance of individual logistic regression coefficients was tested using the model χ2 test and Wald Statistic. The model's performance was evaluated using percent correct predictions and the Kolmogorov-Smirnov Test.

III. Research Findings

The preliminary data analysis revealed that age, number of dependents, downpayment to unit price ratio, and income to balance ratio are significant predictors of payment behaviour. Gender, civil status, and length of residence were found to be insignificant and excluded from the model. The logistic regression model showed that the payment completion probability decreases with age and number of dependents. On the other hand, a higher downpayment-to-unit price ratio and income-to-balance ratio increase the likelihood of payment completion.

IV. Evaluation of the Model

The model's performance was evaluated using percent correct predictions, which indicated that it can correctly predict payment behaviour in the range of 55.1% to 68.9% when individual variables are considered. When all significant variables are included in the final model, the percentage of correct predictions increases to 71.5%.

V. Qualification Tests of Applicants

The credit scoring model was used to identify potential combinations of borrower qualifications that indicate a higher probability of payment completion. However, the results obtained from the Kolmogorov-Smirnov Test suggested that further validation with larger sample sizes is necessary to improve the model's accuracy and consistency.

VI. Conclusion

The credit scoring model developed for motorcycle financing showed promising results in identifying significant predictors of payment behaviour. Age, number of dependents, downpayment to unit price ratio, and income to balance ratio were found to be crucial factors in assessing creditworthiness. However, the model's performance requires further validation and refinement through larger sample sizes and additional tests. Nonetheless, the credit scoring system is considered relevant as a complementary strategy to other risk management approaches for the motorcycle financing company.

VII. Future Directions

Future research should focus on expanding the sample size and conducting follow-up studies to validate and improve the credit scoring model. Additionally, incorporating other relevant variables and exploring more advanced modelling techniques may enhance the accuracy and reliability of the credit scoring system. Such efforts will contribute to better risk management and decision-making in the motorcycle financing industry.