Insurance
20 columns
202 rows
8 formats

Health Insurance Claim Patterns

This dataset provides detailed records of health insurance claims, including demographic information, clinical codes, financial details, and process statuses. It is ideal for analyzing claim patterns, detecting potential fraud, and optimizing insurance workflows. The inclusion of both member and provider data enables comprehensive trend analysis and risk assessment.

opened 8 times
last updated 20 Aug 2025
by GoMask

The brief that made it

Fraud detection and risk scoring for insurance claims

Sample rows

preview · 8 of 202 rows · all 20 columns

claim_idstring	provider_typestring	claim_amountfloat	is_fraud_flaggedboolean	policy_idstring	member_idstring	claim_datedate	claim_statusstring	paid_amountfloat	diagnosis_codestring	procedure_codestring	provider_idstring	member_genderstring	member_birth_datedate	member_zip_codestring	admission_datedate	discharge_datedate	length_of_stayinteger	claim_typestring	submission_channelstring
A8F5T2ZK	physician	325.5	false	POL2222	MEM10001	2019-03-17	approved	320	J45.90	99213	PRV1001	female	1984-08-23	90210	blank	blank	blank	outpatient	online
Q1X8V7ML	dental	92	false	POL1212	MEM10002	2020-11-05	submitted	blank	K02.53	D2150	PRV1002	male	2009-04-11	10001	blank	blank	blank	dental	provider_portal
M3G6C2BQ	lab	585	false	POL3333	MEM10003	2022-06-21	approved	585	E11.9	83036	PRV1003	female	1956-10-05	60614	blank	blank	blank	outpatient	online
S9Y2L5PJ	vision	49.99	false	POL2222	MEM10001	2022-01-14	pending	blank	H52.4	S0620	PRV1004	female	1984-08-23	90210	blank	blank	blank	vision	online
N8J3R4KT	hospital	14500	false	POL1212	MEM10004	2023-09-02	approved	14490	I10	99223	PRV1005	male	1952-02-16	77056	2023-08-24	2023-08-30	6	inpatient	paper
X4D7N6ZU	clinic	6300	false	POL4444	MEM10005	2021-03-10	denied	0	S13.4	97110	PRV1006	female	1989-07-29	V6C-1A6	blank	blank	blank	outpatient	provider_portal
B5F9K2WY	pharmacy	215.75	false	POL5555	MEM10006	2018-07-22	approved	215.75	N18.3	J3030	PRV1007	male	1967-05-03	80808	blank	blank	blank	pharmacy	online
K5U6Q9AX	vision	89.99	false	POL2222	MEM10007	2021-12-19	approved	89.99	H25.13	S0621	PRV1008	female	2011-08-13	60614	blank	blank	blank	vision	online
V3T7M2BR	clinic	480	false	POL6666	MEM10008	2020-04-07	pending	blank	M54.5	97140	PRV1009	male	1978-12-09	10001	blank	blank	blank	outpatient	online
F2N7C3QK	lab	2560	false	POL1212	MEM10009	2018-02-24	denied	0	E78.5	80053	PRV1010	other	1975-11-30	99999	blank	blank	blank	outpatient	paper
U1H6K3YX	hospital	10250	false	POL7777	MEM10010	2023-07-18	approved	10100	I21.9	92928	PRV1011	male	1948-06-02	A1B-2C3	2023-07-08	2023-07-15	7	inpatient	paper
E9K2S3DL	clinic	8610	true	POL8888	MEM10011	2021-09-25	under_review	blank	C50.311	G0121	PRV1012	female	1961-01-20	A0A-0A0	blank	blank	blank	outpatient	provider_portal
J6L3M7BV	physician	120	false	POL3333	MEM10003	2024-02-03	approved	119	K21.9	99214	PRV1013	female	1956-10-05	60614	blank	blank	blank	outpatient	online
P5Z9G2UX	hospital	32500	false	POL9999	MEM10012	2022-10-28	approved	32450	C34.90	99223	PRV1014	male	1943-03-17	77056	2022-10-13	2022-10-20	7	inpatient	paper
R2H5L8QJ	dental	57.99	false	POL1010	MEM10013	2020-08-01	approved	57.99	K04.7	D1110	PRV1015	female	2012-10-30	90210	blank	blank	blank	dental	online
W8H2S9LK	vision	210	false	POL2222	MEM10007	2021-01-02	submitted	blank	H52.2	S0622	PRV1016	female	2011-08-13	60614	blank	blank	blank	vision	online
D6Y1F3KR	pharmacy	0.01	false	POL5555	MEM10006	2019-11-16	approved	0.01	R53.83	J3031	PRV1017	male	1967-05-03	80808	blank	blank	blank	pharmacy	online
H4M9R6AX	physician	399.95	false	POL1111	MEM10014	2018-05-25	pending	blank	L03.11	99215	PRV1018	male	1985-02-18	60614	blank	blank	blank	outpatient	online
T3B6K1VL	lab	500	false	POL1212	MEM10009	2023-03-28	approved	500	E66.9	80053	PRV1019	other	1975-11-30	99999	blank	blank	blank	outpatient	paper
G7L2P5MD	clinic	330	false	POL4444	MEM10005	2021-11-28	approved	325	Z00.00	99395	PRV1020	female	1989-07-29	V6C-1A6	blank	blank	blank	outpatient	provider_portal

What the 202 rows show

from the 202-row sample

Hospital (provider type) stands out: mean claim_amount is 11,832, against 1,302 for the rest.

5%is_fraud_flagged = true
220.4median claim_amount
4member genders
4submission channels
6claim statuses
6claim types

Mean claim_amount by provider_type202 rows

claim_amount202 rows, in bands of 5,000

Median 220.4, from 0.01 to 32,500.

policy_id202 rows · top 10 of 15 values

POL555532
POL222230
POL121229
POL333328
POL888820
POL999915
POL777710
POL66668
POL44447
POL10017

20 columns by typefrom the column list below

string 12
integer 1
float 2
date 4
boolean 1

Columns

20 columns in four groups

blueprint · 20 columns
column	type	description	example
Text 12 columns
`claim_id`	string	Unique identifier for each insurance claimunique	A8F5T2ZK
`policy_id`	string	Unique identifier for the insurance policy associated with the claim	POL2222
`member_id`	string	Unique identifier for the insured member making the claim	MEM10001
`claim_status`	string	Current status of the claim6 values	approved
`diagnosis_code`	string	Primary ICD diagnosis code associated with the claim	J45.90
`procedure_code`	string	Primary CPT/HCPCS procedure code billed in the claimoptional	99213
`provider_id`	string	Unique identifier for the healthcare provider or facility	PRV1001
`provider_type`	string	Type of provider (e.g., hospital, clinic, physician)6 values	physician
`member_gender`	string	Gender of the insured membermale · female · other · unknown	female
`member_zip_code`	string	Postal code of the member's residence11 codes · optional	90210
`claim_type`	string	Type of claim (e.g., inpatient, outpatient, pharmacy)6 values	outpatient
`submission_channel`	string	Channel through which the claim was submittedonline · paper · phone · provider_portal · other · optional	online
Numbers 3 columns
`claim_amount`	float	Total monetary amount claimed0 or more	325.5
`paid_amount`	float	Amount paid out by the insurer for this claim0 or more · optional	320
`length_of_stay`	integer	Number of days spent in facility (if applicable)0 or more · optional	6
Dates and times 4 columns
`claim_date`	date	Date when the claim was submitted	2019-03-17
`member_birth_date`	date	Birth date of the insured member	1984-08-23
`admission_date`	date	Date of hospital or facility admission (if applicable)optional	2023-08-24
`discharge_date`	date	Date of hospital or facility discharge (if applicable)optional	2023-08-30
True or false 1 column
`is_fraud_flagged`	boolean	Indicates if the claim is flagged as potentially fraudulentoptional	false

Use it for

An insurance dashboard
The is_fraud_flagged rate, claim_amount by provider_type and a breakdown of policy_id. Excel, Power BI or Tableau.
Why do the 29 hospital rows have a mean claim_amount of 11,832?
A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
Claims202
A8F5T2ZK325.5physician
E9K2S3DL8610clinic
Y6P8X4JQ4900clinic
A software demo
Believable claims with policy_id, member_id and claim_date to fill a screen in front of a buyer.

This dataset202 rows20 columns

Yours1,000 rows20 columnsmember_zip_code: UK only

blueprint · health-insurance-claim-patterns

Behind this dataset

Same schema. As many rows as you need.

These 202 rows came out of a blueprint — 20 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

Type of service validated for each claim
Duplicate claims deduplicated
Claim amounts are ranged and realistic
Claim status (approved/denied) included

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: health-insurance-claim-patterns

What should your data show?

No signup. No card.

Sample rows

What the 202 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?