The Altair Community is migrating to a new platform to provide a better experience for you. The RapidMiner Community will merge with the Altair Community at the same time. In preparation for the migration, both communities are on read-only mode from July 15th - July 24th, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here.
Options

Help for Creditworthy Scoring Model

ferdinand_papaferdinand_papa Member Posts: 7 Contributor I
Hello Guys,

I hope you can assist me in my task. 

We need to develop a model to predict creditworthiness raiting within a given dataset. 
I have given you the training set its called "zahlungsausfall_train.txt" as well as the set to predict "zahlungsausfall_class.txt".

In the training dataset you will find the attribute "TARGET_BETRUG" it can either be YES or NO it means basically if someone is creditworthy or not creditworthy.  

The goal is to create a "CLASS" that Contains "H" for NO and "N" for YES" 

As you can see in my training data Set If you let it run through it converts "TARGET_BETRUG" into "Klasse" and therefore it puts them into the 2 categories N or H. 

The thing is I tried to get it done with a decision tree.. as you can see in the process but as soon as I let it run through it just gives me N in the dataset where we are supposed to predict correctly. 

My question is which parameters or operators do I have to add or adjust to get a similar outcome as in the training set.


greetings



Answers

  • Options
    varunm1varunm1 Moderator, Member Posts: 1,207 Unicorn
    Hello @ferdinand_papa

    I tried your model with Decision Tree and see that it is unable to predict 'H' label. I cannot say it is wrong as your training set does not have an output label to get the performance. I used a Gradient Boosted tree algorithm which is complex and powerful and observe that it is able to predict both 'H' and 'N' classes for your test data. But as there are no labels (outputs) for your test data I cannot comment whether the performance is good or not.

    Do you by any chance have labels for your test data which you are applying for apply model operator? This will provide you with performance.

    Thanks
    Regards,
    Varun
    https://www.varunmandalapu.com/

    Be Safe. Follow precautions and Maintain Social Distancing

  • Options
    ferdinand_papaferdinand_papa Member Posts: 7 Contributor I
    I think I finished the model.
    If you want you can check for any mistakes :)

    regards
Sign In or Register to comment.