Insurance
22 columns
200 rows
8 formats

Healthcare Claims Fraud Analysis

This dataset contains detailed records of healthcare insurance claims, including claim amounts, medical codes, patient and provider information, and fraud indicators. It is designed to support advanced fraud detection and analysis by capturing submission patterns, approval outcomes, and relevant metadata for each claim. The dataset is ideal for insurers, data scientists, and healthcare analysts seeking to identify fraudulent activity and optimize claims processing.

opened 5 times
last updated 20 Aug 2025
by GoMask

The brief that made it

Automated detection of fraudulent healthcare claims

Sample rows

preview · 8 of 200 rows · all 22 columns

claim_idstring	claim_statusstring	claim_amountfloat	fraud_flagboolean	provider_statestring	patient_idstring	provider_idstring	claim_submission_datedate	claim_approval_datedate	approved_amountfloat	diagnosis_codestring	procedure_codestring	service_datedate	fraud_detection_methodstring	submission_channelstring	patient_ageinteger	patient_genderstring	provider_specialtystring	provider_citystring	provider_postal_codestring	provider_countrystring	notesstring
CLM-00001	approved	310.5	false	WA	PAT-00001	PRV-00001	2021-02-15	2021-02-19	310.5	J01.90	99213	2021-02-13	blank	online	34	female	General Practice	Seattle	98101	USA	Routine checkup for upper respiratory symptoms.
CLM-00002	approved	275	false	TX	PAT-00002	PRV-00002	2021-04-06	2021-04-10	275	E11.9	83036	2021-04-03	blank	online	58	male	Endocrinology	Houston	77002	USA	Diabetes management follow-up visit.
CLM-00003	pending	1200	false	IL	PAT-00003	PRV-00003	2021-06-12	blank	blank	I10	93000	2021-06-11	blank	paper	62	female	Cardiology	Chicago	60611	USA	Blood pressure monitoring and EKG performed.
CLM-00004	approved	50	false	TX	PAT-00004	PRV-00004	2021-09-03	2021-09-11	50	Z00.00	99385	2021-09-02	blank	online	27	male	Family Medicine	Austin	78701	USA	Annual adult wellness exam.
CLM-00005	submitted	6000	false	MA	PAT-00005	PRV-00005	2021-11-22	blank	blank	C50.919	19301	2021-11-20	blank	fax	56	female	Surgical Oncology	Boston	02115	USA	Breast mass excision scheduled; awaiting pathology.
CLM-00006	approved	89.99	false	CO	PAT-00006	PRV-00006	2022-01-10	2022-01-13	89.99	S80.011A	12001	2022-01-09	blank	online	17	male	Pediatrics	Denver	80202	USA	Minor laceration repair for high school athlete.
CLM-00007	under_review	4800	true	NV	PAT-00007	PRV-00007	2022-02-07	blank	blank	F32.9	90837	2022-02-05	manual_review_flag	paper	41	female	Psychiatry	Las Vegas	89109	USA	Extended psychotherapy session flagged for review.
CLM-00008	approved	420	false	FL	PAT-00008	PRV-00008	2022-03-15	2022-03-17	420	L60.0	11100	2022-03-12	blank	online	29	male	Dermatology	Miami	33101	USA	Removal of benign skin lesion.
CLM-00009	approved	11500	false	MN	PAT-00009	PRV-00009	2022-04-21	2022-04-29	11500	M16.9	27447	2022-04-19	blank	fax	73	female	Orthopedic Surgery	Minneapolis	55401	USA	Total hip replacement; Medicare patient.
CLM-00010	approved	315.75	false	CA	PAT-00010	PRV-00010	2022-05-04	2022-05-06	315.75	H52.4	92014	2022-05-01	blank	online	38	female	Ophthalmology	Los Angeles	90001	USA	Routine eye exam and prescription update.
CLM-00011	submitted	0.5	false	CA	PAT-00011	PRV-00011	2022-06-01	blank	blank	P07.30	99460	2022-05-31	blank	other	0	male	Neonatology	San Diego	92101	USA	Newborn screening minimal administrative fee.
CLM-00012	approved	129.99	false	OH	PAT-00012	PRV-00012	2022-07-21	2022-07-28	129.99	F41.9	90834	2022-07-20	blank	online	15	female	Behavioral Health	Cleveland	44101	USA	Counseling session for anxiety symptoms.
CLM-00013	approved	260	false	OR	PAT-00013	PRV-00013	2022-08-18	2022-08-21	260	K21.9	43239	2022-08-15	blank	online	52	male	Gastroenterology	Portland	97201	USA	Upper GI endoscopy for reflux symptoms.
CLM-00014	pending	430	false	NY	PAT-00014	PRV-00014	2022-09-13	blank	blank	E66.9	99401	2022-09-12	blank	online	36	female	Internal Medicine	New York	10001	USA	Dietary counseling and wellness exam.
CLM-00015	approved	75	false	TX	PAT-00015	PRV-00015	2022-10-19	2022-10-21	75	B34.9	87804	2022-10-18	blank	online	21	male	General Practice	Dallas	75201	USA	Influenza rapid testing for college student.
CLM-00016	approved	6900	false	TX	PAT-00016	PRV-00016	2022-11-27	2022-11-30	6900	C18.9	44140	2022-11-24	blank	paper	68	female	Surgical Oncology	Houston	77098	USA	Colon resection for carcinoma.
CLM-00017	under_review	200000	true	NY	PAT-00017	PRV-00017	2022-12-16	blank	blank	R65.21	99285	2022-12-15	large_amount_check	online	53	male	Emergency Medicine	New York	10018	USA	High-cost critical care flagged for outlier review.
CLM-00018	approved	95	false	CA	PAT-00018	PRV-00018	2023-01-04	2023-01-08	95	E78.5	80061	2023-01-03	blank	online	45	female	Internal Medicine	San Francisco	94105	USA	Lipid panel and cholesterol screening.
CLM-00019	approved	140	false	WA	PAT-00019	PRV-00019	2023-02-22	2023-02-24	140	Z23	90715	2023-02-21	blank	online	32	female	General Practice	Seattle	98104	USA	Adult Tdap booster vaccine visit.
CLM-00020	approved	75	false	OR	PAT-00020	PRV-00020	2023-03-07	2023-03-11	75	R50.9	87880	2023-03-05	blank	online	26	male	Family Medicine	Portland	97209	USA	Rapid strep test and fever evaluation.

What the 200 rows show

from the 200-row sample

Under_review (claim status) stands out: 15 of its 18 rows have fraud_flag = true, against 3 of 182 for the rest.

9%fraud_flag = true
217.9median claim_amount
3fraud detection methods
4patient genders
5submission channels
25provider specialties

Fraud flag rate by claim_statusfraud_flag = true

claim_amount200 rows, in bands of 20k

Median 217.9, from 0.01 to 200,000.

provider_state200 rows · top 10 of 29 values

TX30
CA28
WA16
FL13
CO11
OH10
IL9
NV8
OR8
NY8

22 columns by typefrom the column list below

string 15
integer 1
float 2
date 3
boolean 1

Columns

22 columns in four groups

blueprint · 22 columns
column	type	description	example
Text 15 columns
`claim_id`	string	Unique identifier for each healthcare claimunique	CLM-00001
`patient_id`	string	Unique identifier for the patient submitting the claim	PAT-00001
`provider_id`	string	Unique identifier for the healthcare provider associated with the claim	PRV-00001
`claim_status`	string	Current status of the claim (e.g., submitted, approved, rejected, pending)submitted · approved · rejected · pending · under_review	approved
`diagnosis_code`	string	Medical diagnosis code (ICD or similar) associated with the claim	J01.90
`procedure_code`	string	Medical procedure code (CPT or similar) billed in the claim	99213
`fraud_detection_method`	string	Method or algorithm used to flag the claim as fraudulent3 methods · optional	manual_review_flag
`submission_channel`	string	Channel through which the claim was submitted (e.g., online, paper, phone)online · paper · phone · fax · other · optional	online
`patient_gender`	string	Gender of the patientmale · female · other · unknown · optional	female
`provider_specialty`	string	Medical specialty of the provideroptional	General Practice
`provider_city`	string	City where the provider is locatedoptional	Seattle
`provider_state`	string	State where the provider is locatedoptional	WA
`provider_postal_code`	string	Postal code of the provider's locationoptional	98101
`provider_country`	string	Country of the provideroptional	USA
`notes`	string	Additional notes or comments regarding the claim or fraud investigationoptional	Routine checkup for upper…
Numbers 3 columns
`claim_amount`	float	Total monetary amount requested in the claim0 or more	310.5
`approved_amount`	float	Monetary amount approved for the claim0 or more · optional	310.5
`patient_age`	integer	Age of the patient at the time of claim submission0 to 120 · optional	34
Dates and times 3 columns
`claim_submission_date`	date	Date when the claim was submitted	2021-02-15
`claim_approval_date`	date	Date when the claim was approved or rejectedoptional	2021-02-19
`service_date`	date	Date when the medical service was provided	2021-02-13
True or false 1 column
`fraud_flag`	boolean	Indicator if the claim is suspected or confirmed as fraudulent	false

Use it for

An insurance dashboard
The fraud_flag rate, claim_amount by claim_status and a breakdown of provider_state. Excel, Power BI or Tableau.
Why do 18 of 200 rows have fraud_flag = true?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Claims200
CLM-00001310.5approved
CLM-000074800under_re…
CLM-00017200000under_re…
A software demo
Believable claims with patient_id, provider_id and claim_submission_date to fill a screen in front of a buyer.

This dataset200 rows22 columns

Yours1,000 rows22 columnsprovider_city: UK only

blueprint · healthcare-claims-fraud-analysis

Behind this dataset

Same schema. As many rows as you need.

These 200 rows came out of a blueprint — 22 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

Include claim type and patient info
Flag suspicious claims
Track outcome of investigations
Exclude denied but valid claims

Rows1,000 rows10,000 rows100,000 rows1,000,000 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: healthcare-claims-fraud-analysis

What should your data show?

No signup. No card.

Sample rows

What the 200 rows show

Columns

Use it for

An insurance dashboard

A root-cause class exercise

A software demo

Make it yours.

Same schema. As many rows as you need.

More in Insurance

What should your data show?