Loan Default Prediction Dataset

This dataset provides detailed borrower profiles and comprehensive loan performance records, including payment history and default status, to support advanced risk modeling and mitigation strategies. It is ideal for predictive analytics, credit scoring, and financial risk assessment in lending environments.

  • opened 21 times
  • last updated 20 Aug 2025
  • by GoMask
The brief that made it

Predicting loan default risk using machine learning models

Sample rows

preview · 8 of 200 rows · all 25 columns
loan_idstringloan_purposestringloan_term_monthsintegerloan_default_flagbooleanborrower_employment_statusstringborrower_idstringborrower_namestringborrower_dobdateborrower_genderstringborrower_annual_incomefloatborrower_credit_scoreintegerborrower_address_streetstringborrower_address_citystringborrower_address_statestringborrower_address_postal_codestringborrower_address_countrystringloan_amountfloatloan_interest_ratefloatloan_issue_datedateloan_maturity_datedateloan_statusstringloan_default_datedateloan_total_payments_madefloatloan_number_of_payments_missedintegerloan_last_payment_datedate
LN000001home180falseemployedBR10001Jacob Thompson1987-09-04male820006921429 Maple AveHoustonTX77002USA2600004.92020-07-202035-07-20activeblank3600002024-05-01
LN000002personal36falseemployedBR10002Priya Iyer1993-02-12female54000776B-17 Saraswati RdMumbaiMH400005India95009.22021-03-152024-03-15closedblank1185002024-03-15
LN000003auto12falseretiredBR10003Lucas Brown1961-11-24male0441278 Pine StPortlandOR97204USA650019.52023-02-102024-02-10delinquentblank320022023-12-01
LN000004business60falseself-employedBR10004Emily Zhang1983-06-20female12400073448 Yonge StTorontoONM5E1X8Canada350007.32022-09-012027-09-01activeblank980002024-05-01
LN000005education18falsestudentBR10005Akash Sharma1999-12-18male03153/48 Sector 10DelhiDL110081India230015.12022-01-202023-07-20delinquentblank78032023-04-20
LN000006auto24falseemployedBR10006Anna Kowalski1974-03-05female6700066515 Nowa StWarsawMaz00-950Poland120006.82023-04-232025-04-23activeblank340002024-05-20
LN000007business48falseself-employedBR10007Mohammed Al-Sayed1980-08-17male14800070132 King Faisal RdRiyadhRiyadh11564Saudi Arabia870008.52022-10-102026-10-10activeblank1770002024-05-01
LN000008personal12falseretiredBR10008Linda Miller1954-05-11female12000362433 Oak StreetClevelandOH44101USA220022.32023-06-212024-06-21activeblank120012024-03-15

What the 200 rows show

from the 200-row sample

Home (loan purpose) stands out: mean loan_term_months is 210.0, against 38.0 for the rest.

  • 5%loan_default_flag = true
  • 36median loan_term_months
  • 4borrower genders
  • 4loan statuses
  • 45borrower address countries
  • 52,400median borrower_annual_income
Mean loan_term_months by loan_purpose200 rows
0200400210.0home28 rows38.4auto50 rows11.9educat…17 rows85.7busine…35 rows20.2person…70 rows
loan_term_months200 rows, in bands of 50
0751501471861490330200400loan_term_months →

Median 36, from 1 to 360.

borrower_employment_status200 rows · 5 values
  1. employed99
  2. self-employed49
  3. retired28
  4. student17
  5. unemployed7
25 columns by typefrom the column list below
  • string 12
  • integer 3
  • float 4
  • date 5
  • boolean 1

Columns

25 columns in four groups
blueprint · 25 columns
columntypedescriptionexample
Text 12 columns
loan_idstringUnique identifier for each loan issueduniqueLN000001
borrower_idstringUnique identifier for each borrowerBR10001
borrower_namestringFull name of the borrowerJacob Thompson
borrower_genderstringGender of the borrowermale · female · other · prefer_not_to_say · optionalmale
borrower_employment_statusstringCurrent employment status of the borroweremployed · self-employed · unemployed · student · retiredemployed
borrower_address_streetstringStreet address of the borroweroptional1429 Maple Ave
borrower_address_citystringCity of the borrower's addressoptionalHouston
borrower_address_statestringState or province of the borrower's addressoptionalTX
borrower_address_postal_codestringPostal code of the borrower's addressoptional77002
borrower_address_countrystringCountry of the borrower's addressoptionalUSA
loan_purposestringPurpose for which the loan was taken6 values · optionalhome
loan_statusstringCurrent status of the loanactive · closed · defaulted · delinquentactive
Numbers 7 columns
borrower_annual_incomefloatAnnual income of the borrower in local currency0 or more82000
borrower_credit_scoreintegerCredit score of the borrower at the time of loan application300 to 850692
loan_amountfloatTotal amount of the loan issued0 or more260000
loan_term_monthsintegerDuration of the loan in months1 or more180
loan_interest_ratefloatAnnual interest rate applied to the loan (%)0 to 1004.9
loan_total_payments_madefloatTotal amount paid by the borrower towards the loan0 or more · optional36000
loan_number_of_payments_missedintegerNumber of scheduled payments missed by the borrower0 or more · optional0
Dates and times 5 columns
borrower_dobdateDate of birth of the borrower1987-09-04
loan_issue_datedateDate the loan was issued2020-07-20
loan_maturity_datedateDate the loan is scheduled to be fully repaid2035-07-20
loan_default_datedateDate the loan was marked as defaulted (if applicable)optional2024-04-15
loan_last_payment_datedateDate of the most recent payment made on the loanoptional2024-05-01
True or false 1 column
loan_default_flagbooleanIndicates whether the loan has defaulted (true/false)false

15 SQL practice questions for the Loan Default Prediction Dataset

Written for this data and checked against it: 12 SQL and 3 Power BI exercises from beginner to advanced. Try the first three free; the practice kit has all 15, a starter .sql file and an answer key with every expected result.

  1. 01BeginnerFreeDISTINCT · ORDER BY

    Distinct loan purposes

    Return each distinct loan_purpose found in the data, sorted alphabetically. The result should have one column: loan_purpose.

    Tables: loan_default_prediction_dataset · your result: 1 columns, 5 rows
  2. 02BeginnerFreeGROUP BY · COUNT

    Loan rows per status

    Count the rows for each loan_status. Return the columns loan_status and loan_count, sorted by loan_count descending and then by loan_status ascending.

    Tables: loan_default_prediction_dataset · your result: 2 columns, 4 rows
  3. 03BeginnerFreeGROUP BY · AVG · SUM

    Average loan amount by purpose

    For each loan_purpose, return loan_purpose, avg_amount (the average loan_amount rounded to 2 decimals) and total_amount (the sum of loan_amount rounded to 2 decimals). Sort by loan_purpose ascending.

    Tables: loan_default_prediction_dataset · your result: 3 columns, 5 rows
  1. 04High-income employed borrowersBeginner
  2. 05Defaults by employment status tablePower BI
  3. 06Purposes with many missed paymentsIntermediate
  4. 07Credit score bandsIntermediate
  5. 08Loans above average amountIntermediate
  6. 09Issue year cohortsIntermediate
  7. 10Country vs overall average incomePower BI
  8. 11Rank loans by amount within purposeAdvanced
  9. 12Running total of defaulted loan amountsAdvanced
  10. 13Share of loan volume by purposeAdvanced
  11. 14Gap between consecutive home loan datesAdvanced
  12. 15Interest rate anomalies by purposePower BI

Get the practice kit: the full dataset, all 15 exercises, a starter .sql and the answer key. One-time $3.99.

Get the practice kit · $3.99

Use it for

  • loan default f…5%9 of 200 rowsmean loan term months…210.0home38.4auto11.9educ…85.7busi…

    A finance dashboard

    The loan_default_flag rate, loan_term_months by loan_purpose and a breakdown of borrower_employment_status. Excel, Power BI or Tableau.

  • Why do the 28 home rows have a mean loan_term_months of 210.0?

    A root-cause class exercise

    Hand out the rows and one question. The answer is in the data, not in the brief.

  • A software demo

    Believable loans with borrower_id, borrower_name and borrower_dob to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 25 columns, your size and your rules. See 20 rows before you pay.

Preview 20 rows free

1,000 rows: $1.99 · 10,000: $12.99One-time. No subscription. All prices

This dataset200 rows25 columns
Yours1,000 rows25 columnsborrower_address_street: UK only

blueprint · loan-default-prediction-dataset

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 25 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.

Rules it was built with
  • Log borrower income and history
  • Include loan type and amount
  • Record payment schedule adherence
  • Flag high-risk applicants
Rows
Open the blueprint in Data Factory

1 credit per row. Preview 20 rows free. Buy rows for the full run.

Exports
CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
Licence
yours to use, including commercially
API slug
loan-default-prediction-dataset

More in Finance

Browse all
Also in FinanceMortgage Default Prediction DataPersonal Finance Budgeting RecordsBanking Customer Support Chat LogsAll 1,966 datasets
In collectionsFinancial Data Hub: 25 Free Sample Datasets for Analysis

What should your data show?

Preview 20 rows free
No signup. No card.