I am new to Knime and was wondering which nodes to use in order to clean and mine data, also which techniques would you suggest in order to model the data. I need to decide wether each customer will default on a loan within the next two years based on 6 variables, which are different types of data such a percentages and integers. I think I will use logistic regression but is there any other techniques you could suggest? The data has also been split into a test and training set, which I will attach.
you can find an example for credit scoring here in our use cases
The workflow is also available on the example server: