I created this github page to present the German credit risk report .

This study aims at adressing a classification problem by using the the applicant demographic and socio-economic profiles of german credit data to examine the risk of lending loan to the customer. I assessed the performance of different Machine learning algorithms (Logistic regression model , Decision tree, random forests, Support vector machines ,neural networks, Lasso ) in terms of overall accuracy. For the model optimization, i conducted a comparative assessment of different models combining the effects of Gini, KS, F1-score, balanced accuracy and the area under the ROC curve (AUC) values.

check my repository here : https://github.com/Mono33/GermanCreditRisk

You will find the following files:

GermanCredit_Rcode.R : Rcode in line with the reports and which generates all accuracy metrics,

PDFReport_GermanRisk.pdf : German credit risk report in pdf format ( download it on your pc),

Report_GermanRisk.Rmd : Report in rmd file used to generate this web page.