Data
Fraud-Detection-Updated)

Fraud-Detection-Updated)

active ARFF CC BY 4.0 Visibility: public Uploaded 13-11-2024 by Anna Wiewer
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Updated Fraud Detection dataset with nominal target for binary classification.

29 features

bad_flag (target)string2 unique values
0 missing
dpd_5_cntnumeric8 unique values
3481 missing
dpd_15_cntnumeric6 unique values
3481 missing
dpd_30_cntnumeric4 unique values
3481 missing
close_loans_cntnumeric21 unique values
15 missing
federal_district_nmnumeric9 unique values
0 missing
payment_type_0numeric9 unique values
0 missing
payment_type_1numeric28 unique values
0 missing
payment_type_2numeric26 unique values
0 missing
payment_type_3numeric24 unique values
0 missing
payment_type_4numeric7 unique values
0 missing
payment_type_5numeric1 unique values
0 missing
past_billings_cntnumeric21 unique values
248 missing
score_1numeric1274 unique values
649 missing
score_2numeric47 unique values
3917 missing
agenumeric51 unique values
0 missing
gendernumeric2 unique values
0 missing
rep_loan_date_yearnumeric3 unique values
0 missing
rep_loan_date_monthnumeric12 unique values
0 missing
rep_loan_date_daynumeric31 unique values
0 missing
rep_loan_date_weekdaynumeric7 unique values
0 missing
first_loan_yearnumeric2 unique values
0 missing
first_loan_monthnumeric12 unique values
0 missing
first_loan_daynumeric31 unique values
0 missing
first_loan_weekdaynumeric7 unique values
0 missing
first_overdue_date_yearnumeric2 unique values
3481 missing
first_overdue_date_monthnumeric12 unique values
3481 missing
first_overdue_date_daynumeric19 unique values
3481 missing
first_overdue_date_weekdaynumeric8 unique values
0 missing
Show all 29 features

19 properties

NumberOfInstances
4156
Number of instances (rows) of the dataset.
NumberOfFeatures
29
Number of attributes (columns) of the dataset.
NumberOfClasses
2
Number of distinct values of the target attribute (if it is nominal).
NumberOfMissingValues
25715
Number of missing values in the dataset.
NumberOfInstancesWithMissingValues
4156
Number of instances with at least one value missing.
NumberOfNumericFeatures
28
Number of numeric attributes.
NumberOfSymbolicFeatures
0
Number of nominal attributes.
PercentageOfBinaryFeatures
0
Percentage of binary attributes.
PercentageOfInstancesWithMissingValues
100
Percentage of instances having missing values.
PercentageOfMissingValues
21.34
Percentage of missing values.
AutoCorrelation
1
Average class difference between consecutive instances.
PercentageOfNumericFeatures
96.55
Percentage of numeric attributes.
Dimensionality
0.01
Number of attributes divided by the number of instances.
PercentageOfSymbolicFeatures
0
Percentage of nominal attributes.
MajorityClassPercentage
89.97
Percentage of instances belonging to the most frequent class.
MajorityClassSize
3739
Number of instances belonging to the most frequent class.
MinorityClassPercentage
10.03
Percentage of instances belonging to the least frequent class.
MinorityClassSize
417
Number of instances belonging to the least frequent class.
NumberOfBinaryFeatures
0
Number of binary attributes.
Show all 19 properties

1 tasks

Supervised Classification on Fraud-Detection-Updated)
0 runs - estimation_procedure: 33% Holdout set - target_feature: bad_flag
Define a new task