Claims Fraud Detection Dataset
This dataset provides granular insurance claims data with fraud labels, customer demographics, policy details, and suspicious pattern indicators. It is ideal for training fraud detection models, analyzing risk factors, and supporting operational audits in the insurance sector. The dataset enables insurers and analysts to identify fraud trends, profile risky customers, and optimize claim review processes.
Sample rows
preview · 8 of 200 rows · all 24 columns| claim_idstring | claim_typestring | customer_ageinteger | is_fraudboolean | customer_statestring | policy_idstring | customer_idstring | claim_datedate | incident_datedate | claim_amountfloat | claim_statusstring | customer_genderstring | customer_occupationstring | customer_citystring | customer_postal_codestring | customer_countrystring | policy_start_datedate | policy_end_datedate | policy_typestring | num_previous_claimsinteger | num_previous_fraud_claimsinteger | incident_descriptionstring | fraud_reasonstring | suspicious_patternsstring |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CLM-00001 | auto | 29 | false | CA | POL-10001 | CUST-10001 | 2023-06-15 | 2023-06-10 | 6275.45 | approved | male | software engineer | San Francisco | 94107 | USA | 2022-01-01 | 2025-01-01 | comprehensive | 1 | 0 | Minor collision at busy intersection, rear bumper damage. | blank | blank |
| CLM-00002 | health | 24 | false | ON | POL-10002 | CUST-10002 | 2023-07-03 | 2023-06-25 | 450 | approved | female | nurse | Toronto | M5V2T6 | Canada | 2021-09-15 | 2024-09-15 | health | 0 | 0 | Sprained ankle during sports event, required medical attention. | blank | blank |
| CLM-00003 | life | 67 | false | LON | POL-10003 | CUST-10003 | 2022-11-18 | 2022-11-16 | 1200000 | approved | male | retired | London | SW1A 1AA | UK | 2014-03-01 | 2024-03-01 | life | 2 | 0 | Policyholder deceased after long-term illness, claim submitted by beneficiary. | blank | blank |
| CLM-00004 | home | 45 | false | NSW | POL-10004 | CUST-10004 | 2024-01-20 | 2024-01-18 | 3100.99 | under_review | female | accountant | Sydney | 2000 | Australia | 2020-01-01 | 2025-01-01 | home | 2 | 0 | Water leakage from upstairs bathroom damaged kitchen ceiling. | blank | blank |
| CLM-00005 | other | 32 | false | BE | POL-10005 | CUST-10005 | 2023-12-12 | 2023-12-09 | 155 | submitted | male | travel blogger | Berlin | 10115 | Germany | 2023-12-01 | 2024-01-10 | travel | 0 | 0 | Lost luggage during international travel from Berlin to Oslo. | blank | blank |
| CLM-00006 | auto | 38 | false | NY | POL-10006 | CUST-10006 | 2022-04-11 | 2022-04-10 | 8900.75 | approved | female | civil engineer | New York | 10001 | USA | 2021-06-01 | 2024-06-01 | comprehensive | 1 | 0 | Vehicle hit by fallen tree during thunderstorm, major roof damage. | blank | blank |
| CLM-00007 | health | 0 | false | SG | POL-10007 | CUST-10007 | 2023-01-19 | 2023-01-10 | 300 | approved | unknown | infant | Singapore | 238893 | Singapore | 2022-12-01 | 2024-12-01 | health | 0 | 0 | Child developed high fever, required overnight hospitalization. | blank | blank |
| CLM-00008 | auto | 27 | true | CA | POL-10008 | CUST-10008 | 2023-08-29 | 2023-08-20 | 4930 | under_review | female | waitress | Los Angeles | 90013 | USA | 2021-11-01 | 2024-11-01 | comprehensive | 4 | 2 | Hit-and-run accident on highway, front bumper and headlights damaged. | Discrepancy in accident narrative detected. | Multiple claims within short period, altered documents. |
| CLM-00009 | home | 56 | true | WC | POL-10009 | CUST-10009 | 2022-10-14 | 2022-10-10 | 350000 | rejected | male | real estate agent | Cape Town | 8001 | South Africa | 2018-02-01 | 2023-02-01 | home | 8 | 3 | Large-scale fire destroyed significant portions of the property. | Investigation revealed arson suspicion. | Delayed reporting, previous rejected claims, inconsistent witness accounts. |
| CLM-00010 | health | 34 | false | BC | POL-10010 | CUST-10010 | 2024-04-22 | 2024-04-19 | 820 | submitted | female | lab technician | Vancouver | V6B1A1 | Canada | 2022-04-15 | 2025-04-15 | health | 1 | 0 | Routine surgery with post-operative complications requiring extra care. | blank | blank |
| CLM-00011 | other | 28 | false | ZH | POL-10011 | CUST-10011 | 2023-05-19 | 2023-05-17 | 117 | approved | female | student | Zurich | 8001 | Switzerland | 2023-05-01 | 2023-06-01 | travel | 1 | 0 | Travel delay in Zurich due to airline strike, hotel expenses incurred. | blank | blank |
| CLM-00012 | auto | 44 | true | TK | POL-10012 | CUST-10012 | 2022-09-21 | 2022-09-08 | 17500 | under_review | male | mechanic | Tokyo | 100-0001 | Japan | 2020-03-01 | 2025-03-01 | comprehensive | 7 | 1 | Severe accident with multiple vehicles, complete loss of insured car. | Suspicious vehicle value declared. | Inflated repair estimates, previous large claims. |
| CLM-00013 | life | 52 | false | FL | POL-10013 | CUST-10013 | 2023-03-11 | 2023-03-01 | 1800000 | under_review | female | business owner | Miami | 33101 | USA | 2015-09-01 | 2025-09-01 | life | 3 | 0 | Beneficiary filed claim after passing of insured due to heart attack. | blank | blank |
| CLM-00014 | other | 63 | false | LS | POL-10014 | CUST-10014 | 2022-12-12 | 2022-12-10 | 129 | approved | female | retired | Lisbon | 1100-320 | Portugal | 2022-12-01 | 2023-01-01 | travel | 1 | 0 | Lost passport and hotel booking issues during travel in Lisbon. | blank | blank |
| CLM-00015 | home | 41 | false | GT | POL-10015 | CUST-10015 | 2023-01-07 | 2023-01-06 | 12000.5 | approved | male | geologist | Johannesburg | 2001 | South Africa | 2019-05-01 | 2024-05-01 | home | 6 | 1 | Storm caused roof tiles to break, rainwater entered bedrooms. | blank | blank |
| CLM-00016 | auto | 26 | false | MH | POL-10016 | CUST-10016 | 2022-08-15 | 2022-08-05 | 8800 | submitted | male | mechanic | Mumbai | 400001 | India | 2021-08-01 | 2024-08-01 | comprehensive | 2 | 0 | Rear-end collision during rush hour, moderate damage to trunk. | blank | blank |
| CLM-00017 | health | 22 | false | OS | POL-10017 | CUST-10017 | 2023-09-12 | 2023-09-02 | 285 | approved | female | student | Oslo | 0250 | Norway | 2022-09-01 | 2024-09-01 | health | 0 | 0 | Routine dental check-up, covered under policy. | blank | blank |
| CLM-00018 | life | 59 | true | DXB | POL-10018 | CUST-10018 | 2024-02-02 | 2024-01-28 | 3000000 | approved | female | CEO | Dubai | 00000 | UAE | 2012-02-01 | 2024-02-15 | life | 9 | 5 | Claim for life insurance after sudden passing of policyholder. | Beneficiary relationship unclear, insufficient documentation. | Documents submitted are inconsistent, history of previous fraud claims. |
| CLM-00019 | health | 31 | false | VIC | POL-10019 | CUST-10019 | 2022-02-28 | 2022-02-25 | 250 | approved | male | accountant | Melbourne | 3000 | Australia | 2021-01-01 | 2024-01-01 | health | 2 | 0 | Treatment for minor flu symptoms, doctor consultation fees. | blank | blank |
| CLM-00020 | auto | 35 | false | SG | POL-10020 | CUST-10020 | 2023-05-03 | 2023-05-02 | 6750 | submitted | male | civil engineer | Singapore | 238868 | Singapore | 2022-05-01 | 2025-05-01 | comprehensive | 0 | 0 | Side collision with truck, door and fender damage. | blank | blank |
What the 200 rows show
from the 200-row sampleLife (claim type) stands out: mean customer_
- 18%is_
fraud = true - 36median customer_
age - 4customer genders
- 5claim statuses
- 5policy types
- 17customer countries
Median 36, from 0 to 120.
- string 15
- integer 3
- float 1
- date 4
- boolean 1
Columns
24 columns in four groups| column | type | description | example |
|---|---|---|---|
| Text 15 columns | |||
claim_id | string | Unique identifier for each insurance claimunique | CLM-00001 |
policy_id | string | Unique identifier for the insurance policy associated with the claim | POL-10001 |
customer_id | string | Unique identifier for the customer submitting the claim | CUST-10001 |
claim_type | string | Type of claim (e.g., auto, home, health, life)auto · home · health · life · other | auto |
incident_description | string | Detailed description of the incident leading to the claim | Minor collision at busy i… |
claim_status | string | Current status of the claim (e.g., submitted, under review, approved, rejected, closed)submitted · under_review · approved · rejected · closed | approved |
fraud_reason | string | Short description or code indicating the reason for fraud suspicion (if applicable)optional | Discrepancy in accident n… |
suspicious_patterns | string | Comma-separated codes or keywords indicating detected suspicious patterns (if any)optional | Multiple claims within sh… |
customer_gender | string | Gender of the customermale · female · other · unknown · optional | male |
customer_occupation | string | Occupation of the customeroptional | software engineer |
customer_city | string | City of the customer's residenceoptional | San Francisco |
customer_state | string | State or province of the customer's residenceoptional | CA |
customer_postal_code | string | Postal code of the customer's residenceoptional | 94107 |
customer_country | string | Country of the customer's residenceoptional | USA |
policy_type | string | Type of insurance policy (e.g., comprehensive, third-party, basic)5 types · optional | comprehensive |
| Numbers 4 columns | |||
claim_amount | float | Total monetary amount claimed0 or more | 6275.45 |
customer_age | integer | Age of the customer at the time of claim0 to 120 · optional | 29 |
num_previous_claims | integer | Number of previous claims filed by the customer0 or more · optional | 1 |
num_previous_fraud_claims | integer | Number of previous claims by the customer labeled as fraudulent0 or more · optional | 0 |
| Dates and times 4 columns | |||
claim_date | date | Date when the claim was filed | 2023-06-15 |
incident_date | date | Date when the incident related to the claim occurred | 2023-06-10 |
policy_start_date | date | Date when the insurance policy startedoptional | 2022-01-01 |
policy_end_date | date | Date when the insurance policy ended or will endoptional | 2025-01-01 |
| True or false 1 column | |||
is_fraud | boolean | Label indicating whether the claim is fraudulent (true) or legitimate (false) | false |
Use it for
An insurance dashboard
The is_
fraud rate, customer_ age by claim_ type and a breakdown of customer_ state. Excel, Power BI or Tableau. Why do the 24 life rows have a mean customer_
age of 68.3? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Claims200CLM-0000129autoCLM-0000827autoCLM-0000956home
A software demo
Believable claims with policy_
id, customer_ id and claim_ date to fill a screen in front of a buyer.
This dataset200 rows24 columns
Yours1,000 rows24 columnscustomer_city: UK only
blueprint · claims-fraud-detection-dataset
Behind this dataset
Same schema. As many rows as you need.
These 200 rows came out of a blueprint — 24 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
- Includes structured claims with relevant features
- Fraud label applied based on business rules
- Time and region attributes included
- No real customer data, fully synthetic
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
- claims-fraud-detection-dataset