Datensplitting und Konfusionsmatrix

Kreditrisikomodellierung in R

Lore Dirick

Manager of Data Science Curriculum at Flatiron School

Analyse starten

Screen Shot 2020-06-15 at 8.43.54 AM.png

Trainings- und Testset

Screen Shot 2020-06-15 at 8.43.43 AM.png

Trainings- und Testset

Screen Shot 2020-06-15 at 8.43.14 AM.png

Cross-Validation

Screen Shot 2020-06-15 at 8.43.31 AM.png

Ein Modell bewerten

      test_set$loan_status    model_prediction   
            ...                     ...
 [8066,]      1                       1
 [8067,]      0                       0
 [8068,]      0                       0
 [8069,]      0                       0
 [8070,]      0                       0
 [8071,]      0                       1
 [8072,]      1                       0
 [8073,]      1                       1
 [8074,]      0                       0
 [8075,]      0                       0
 [8076,]      0                       0
 [8077,]      1                       1
 [8078,]      0                       0
        ...                        ...

Ein Modell bewerten

      test_set$loan_status    model_prediction   
            ...                     ...
[8066,]       1                       1
[8067,]       0                       0
 [8068,]      0                       0
 [8069,]      0                       0
 [8070,]      0                       0
 [8071,]      0                       1
 [8072,]      1                       0
 [8073,]      1                       1
 [8074,]      0                       0
 [8075,]      0                       0
 [8076,]      0                       0
 [8077,]      1                       1
 [8078,]      0                       0
 [8079,]      0                       1
        ...                        ...

Tatsächlicher Kreditstatus vs. Modellvorhersage

	Kein Ausfall (0)	Ausfall (1)
Kein Ausfall (0)	8	2
Ausfall (1)	1	3

Ein Modell bewerten

      test_set$loan_status    model_prediction   
            ...                     ...
[8066,]       1                       1
[8067,]       0                       0
 [8068,]      0                       0
 [8069,]      0                       0
 [8070,]      0                       0
 [8071,]      0                       1
 [8072,]      1                       0
 [8073,]      1                       1
 [8074,]      0                       0
 [8075,]      0                       0
 [8076,]      0                       0
 [8077,]      1                       1
 [8078,]      0                       0
 [8079,]      0                       1
        ...                        ...

Tatsächlicher Kreditstatus vs. Modellvorhersage

	Kein Ausfall (0)	Ausfall (1)
Kein Ausfall (0)	TN	FP
Ausfall (1)	FN	TP

Einige Kennzahlen …

Accuracy $$\frac{(8+3)}{14} = 78.57\%$$
Sensitivity $$\frac{3}{(1+3)} = 75\%$$
Specificity $$\frac{8}{(8+2)} = 80\%$$

Tatsächlicher Kreditstatus vs. Modellvorhersage

	Kein Ausfall (0)	Ausfall (1)
Kein Ausfall (0)	8	2
Ausfall (1)	1	3

Lass uns üben!

Kreditrisikomodellierung in R