Dark Mode
Cleaned Credit Card Applicant Data
Finance & Banking Analytics
Tags and Keywords
Trusted By
"No reviews yet"
Free
About
This dataset is a cleaned, merged, and transformed version of an original credit card dataset, initially sourced from @rikdifos [1]. Its primary purpose is to facilitate the implementation of machine learning models designed to determine the eligibility of applicants, classifying them as 'good' or 'bad' [1]. The dataset's preparation specifically addresses the challenge of imbalance data [2], making it suitable for developing robust credit approval prediction systems.
-
Columns
The dataset comprises 21 columns, providing detailed information about credit card applicants:
-
Applicant_ID: Unique identifier for each applicant [2].
-
Applicant_Gender: Gender of the applicant (F or M) [3].
-
Owned_Car: Indicates if the applicant owns a car (1=Yes, 0=No) [3].
-
Owned_Realty: Indicates if the applicant owns property (1=Yes, 0=No) [3].
-
Total_Children: The total number of children the applicant has [4].
-
Total_Income: The applicant's total income [4].
-
Income_Type: Categorisation of the applicant's income source (e.g., Working, Commercial associate) [5, 6].
-
Education_Type: Level of education attained by the applicant (e.g., Secondary / secondary special, Higher education) [6].
-
Family_Status: Marital status of the applicant (e.g., Married, Single / not married) [6].
-
Housing_Type: Type of housing the applicant resides in (e.g., House / apartment, With parents) [7].
-
Owned_Mobile_Phone: Indicates if the applicant owns a mobile phone (1=Yes, 0=No) [7].
-
Owned_Work_Phone: Indicates if the applicant owns a work phone (1=Yes, 0=No) [7, 8].
-
Owned_Phone: Indicates if the applicant owns any phone (1=Yes, 0=No) [8].
-
Owned_Email: Indicates if the applicant owns an email address (1=Yes, 0=No) [8].
-
Job_Title: The applicant's job title (e.g., Laborers, Core staff) [9].
-
Total_Family_Members: The total number of members in the applicant's family [9].
-
Applicant_Age: The applicant's age [10].
-
Years_of_Working: The total number of years the applicant has been working [11].
-
Total_Bad_Debt: The total count of 'Bad Debt' statuses for the applicant [12].
-
Total_Good_Debt: The total count of 'Good Debt' statuses for the applicant [13].
-
Status: The final eligibility status for credit (1=Yes/Allowed, 0=No/Rejected) [14].
-
Distribution
The dataset is provided as a CSV file,
Application_Data.csv, with a size of 7.71 MB [2, 15]. It contains 21 columns and 25.1 thousand valid records [2, 16]. For all listed columns, the data quality is high, with 100% valid entries, and 0% mismatched or missing values [3-14, 16].-
Usage
This dataset is ideal for:
-
Developing and testing machine learning models for credit card approval prediction [1].
-
Building systems to classify applicants as 'good' or 'bad' based on their characteristics [1].
-
Research and experimentation with handling imbalanced datasets in financial applications [2].
-
Analysing factors influencing creditworthiness and applicant behaviour.
-
Coverage
The dataset provides demographic and financial insights into applicants, including gender, age, family composition, income levels, education, employment details, and asset ownership (car, property, phones, email) [3-10]. It also includes their historical debt statuses (good and bad) [12, 13]. The sources do not specify any particular geographical region or time range for the data.
-
License
CC0: Public Domain
-
Who Can Use It
-
Data scientists and machine learning engineers seeking to develop and validate credit scoring models [1].
-
Financial institutions and banking professionals interested in refining their applicant assessment processes and risk management strategies [1].
-
Academic researchers and students studying predictive analytics, credit risk, or data management techniques, particularly concerning data imbalance [1, 2].
-
Dataset Name Suggestions
-
Credit Card Approval Prediction Dataset
-
Cleaned Credit Card Applicant Data
-
Credit Application Predictor Dataset
-
Attributes
Original Data Source: Cleaned Credit Card Applicant Data
QUALITY