Challenges in Developing Risk Models for Crowdlending Platforms

In the digital financial environment, crowdlending has become one of the key forms of alternative financing, enabling direct interaction between investors and borrowers and promoting the democratization of access to capital.

The thesis “Challenges in Developing Risk Models for Crowdlending Platforms” addresses the issue of the effectiveness of traditional credit risk assessment models for small enterprises and startups, and explores the possibilities of their modernization through the use of non-financial indicators, along with the challenges associated with their application.

The theoretical part analyzes the development of crowdlending as an integral component of digital technologies, as well as traditional methods of measuring credit risk (Altman’s Z-score, PD/LGD/EAD models), highlighting their limited applicability for companies without extensive financial histories.

The empirical part includes an analysis that evaluates the accuracy of models based on data from a crowdlending platform. The findings indicate that classical models often misclassify financially sound borrowers as high risk.

To address these inefficiencies, seven “soft information” indicators were incorporated into Altman’s Z-score model, accompanied by a justification of their relevance to default risk and a discussion of the methodological challenges related to data collection and interpretation.

Linear discriminant analysis and logistic regression were applied to evaluate predictive performance. The integration of financial and non-financial information increased the predictive power of the model.

The research confirms that team diversity is closely linked to greater innovativeness, stronger financial performance, and improved access to capital, which shapes the long-term success of startups and influences the valuation of young companies.

In conclusion, it can be stated that the integration of quantitative and qualitative information is crucial for the further development of risk assessment models in crowdlending. Such an approach enhances the effectiveness of credit decision-making, reduces default rates, and strengthens the stability of lending platforms.