|
|
The future of credit scoring modelling using advanced techniques
Čermáková, Jolana ; Krištoufek, Ladislav (advisor) ; Geršl, Adam (referee)
Machine learning is becoming a part of everyday life and has an indisputable impact across large array of industries. In the financial industry, this impact lies particularly in predictive modelling. The goal of this thesis is to describe the basic principles of artificial intelligence and its subset, machine learning. The most widely used machine learning techniques are outlined both in a theoretical and a practical way. As a result, four models were assembled within the thesis. Results and limitations of each model were discussed and these models were also mutually compared based on their individual per- formance. The evaluation was executed on a real world dataset, provided by Home Credit company. Final performance of machine learning methods, measured by the KS and GINI metrics, was either very comparable or even worse than the performance of a traditional logistic regression. Still, the problem may lie in an insu cient dataset, in the improper data prepara- tion, or in inappropriately used algorithms, not necessarily in the models themselves.
|
|
|
Credit Risk of P2P Lending on the Czech Market
Čermáková, Jolana ; Dědek, Oldřich (advisor) ; Čech, František (referee)
This thesis analyzes an emerging peer-to-peer lending industry, while intro- ducing its main features and risks, where the risk of default and its moder- ation gets the most attention. Uniquely provided data from the front Czech platform Zonky containing nearly 6 000 observations serve as a baseline for credit risk modeling. It has been investigated which variables have the largest effect on default on the Czech P2P market. The final model is used to predict the associated probability of default and to compute the credit score for potential borrowers using these online platforms. Results support the fact that education, age, way of living, expenses, marital and employment status, income and the number of children are significant variables when determining the risk of default. Many of these findings are in accordance with previous international papers published on this topic.
|
guest ::
RSS feed.