Smart Ticketing Anomaly Log

This dataset provides a comprehensive log of anomalies detected in urban public transport smart ticketing systems, including fraud attempts, sensor failures, and system inefficiencies. Each record contains detailed event metadata, location, ticket/user context, anomaly type, severity, and resolution status, supporting advanced analytics, AI/ML model training, and smart city infrastructure optimization.

  • last updated 4 Dec 2025
  • by GoMask
The brief that made it

Training and benchmarking AI/ML models for anomaly detection in ticketing systems

Sample rows

preview · 8 of 120 rows · all 19 columns
anomaly_idstringseveritystringfare_amountfloatresolvedbooleancountrystringtimestampdatetimesystem_idstringstation_idstringstation_namestringroute_idstringvehicle_idstringanomaly_typestringdetected_bystringticket_idstringuser_idstringresolution_timestampdatetimecitystringdescriptionstringresolution_notesstring
K7X2-9ZQWcritical2.75trueUS2023-10-17T13:08:51ZMETRO-NYC1STN-1001Grand CentralM-42TRAIN-8120fraudAI_modelTCK-9485271USR-102332023-10-17T15:19:30ZNew YorkMultiple tickets scanned with same user ID at entry gate, potential fare evasion detected.User account suspended and refund issued after investigation.
Q9L8-3XNPhighblankfalseDE2022-07-23T08:41:23ZTRAM-BER1STN-2002AlexanderplatzTR-5TRAM-5547sensor_failureautomated_systemblankblankblankBerlinTicket validator failed to record tap-ins for 3 consecutive hours.blank
S6T1-8WDFmedium2.25trueGB2024-02-12T16:22:09ZBUS-LON2STN-3103Oxford CircusB-12BUS-4531system_errorAI_modelTCK-5872034USR-209452024-02-12T18:02:17ZLondonCentral database sync failed for 40 minutes, causing ticket processing delays.Database restored and affected tickets reconciled.
G3V7-5LXAhigh3.1trueFR2023-04-29T19:12:47ZMETRO-PAR1STN-4104ChâteletM-11TRAIN-3278fraudmanual_reviewTCK-3015829USR-108322023-04-29T21:02:55ZParisSuspicious ticket pattern: single card used for multiple rapid entries.Security notified, card deactivated and user flagged.
H1B5-7RQMlowblanktrueNL2021-12-06T09:57:18ZTRAM-AMS6STN-5205MuseumpleinTR-7TRAM-2321inefficiencyotherblankblank2021-12-06T11:38:14ZAmsterdamTap-out rates lower than expected, indicating possible passenger confusion.Signs updated and staff provided additional guidance.
N5D2-1JQFcriticalblankfalseJP2023-09-05T18:32:55ZMETRO-TYO1STN-6306ShibuyaM-3TRAIN-6549system_errorautomated_systemblankblankblankTokyoGate malfunctions: unable to process tap-ins for 18 minutes.blank
V2U8-6KZThigh2.75trueUS2024-03-13T11:44:32ZBUS-SFO3STN-7407Market St - 3rdB-30BUS-3912fraudautomated_systemTCK-4521783USR-152192024-03-13T13:24:19ZSan FranciscoUnusual fare: ticket scanned for both entry and exit without exit tap.Entry/exit logs matched; user issued warning.
J8F1-4XMGmediumblanktrueES2022-05-19T07:51:27ZTKT-MAD2STN-8508AtochaR-18TRAIN-8812sensor_failureAI_modelblankblank2022-05-19T09:02:35ZMadridContactless readers intermittently offline for 22 minutes.Hardware reset performed, no further issues.

What the 120 rows show

from the 120-row sample
  • 62%resolved = true
  • 2.8median fare_amount
  • 4detected_by values
  • 5anomaly types
severity120 rows by value
020408low7%40medium33%36high30%36critical30%
fare_amount42 rows, in bands of 0.25
0918101146418712.253.25fare_amount →

Median 2.8, from 1.0 to 3.3.

country120 rows · top 10 of 32 values
  1. US11
  2. ES8
  3. TR7
  4. MX6
  5. IN6
  6. DE5
  7. AU5
  8. IT5
  9. CA5
  10. AT5
19 columns by typefrom the column list below
  • string 15
  • float 1
  • datetime 2
  • boolean 1

Columns

19 columns in four groups
blueprint · 19 columns
columntypedescriptionexample
Text 15 columns
anomaly_idstringUnique identifier for each detected anomaly eventuniqueK7X2-9ZQW
system_idstringIdentifier for the smart ticketing system or device where the anomaly occurredMETRO-NYC1
station_idstringUnique identifier for the station or stop where the anomaly was detectedSTN-1001
station_namestringName of the station or stopGrand Central
route_idstringIdentifier for the transit route associated with the anomalyoptionalM-42
vehicle_idstringUnique identifier for the vehicle (bus, train, etc.) involved in the anomalyoptionalTRAIN-8120
anomaly_typestringType of anomaly detected (e.g., fraud, sensor_failure, system_error, inefficiency)fraud · sensor_failure · system_error · inefficiency · otherfraud
severitystringSeverity level of the anomalylow · medium · high · criticalcritical
descriptionstringDetailed description of the anomaly eventoptionalMultiple tickets scanned …
detected_bystringSource of anomaly detection (e.g., automated_system, manual_review, AI_model)automated_system · manual_review · AI_model · otherAI_model
ticket_idstringUnique identifier for the ticket involved in the anomaly (if applicable)optionalTCK-9485271
user_idstringUnique identifier for the user/passenger involved in the anomaly (if applicable)optionalUSR-10233
resolution_notesstringNotes or comments regarding how the anomaly was resolvedoptionalUser account suspended an…
citystringCity where the anomaly occurredNew York
countrystringCountry where the anomaly occurredUS
Numbers 1 column
fare_amountfloatFare amount associated with the ticket or transaction (if applicable)0 or more · optional2.75
Dates and times 2 columns
timestampdatetimeDate and time when the anomaly was detected2023-10-17T13:08:51Z
resolution_timestampdatetimeDate and time when the anomaly was resolved (if applicable)optional2023-10-17T15:19:30Z
True or false 1 column
resolvedbooleanIndicates whether the anomaly has been resolvedtrue

Use it for

  • resolved62%74 of 120 rowsrows by severity8low40medi…36high36crit…

    A transportation dashboard

    The resolved rate, fare_amount by severity and a breakdown of country. Excel, Power BI or Tableau.

  • Why do 74 of 120 rows have resolved = true?

    A class exercise

    Hand out the rows and one question. Everyone works from the same 120 rows.

  • A software demo

    Believable anomalies with timestamp, system_id and station_id to fill a screen in front of a buyer.

Not quite right?

Make it yours.

Same 19 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 dataset120 rows19 columns
Yours1,000 rows19 columnscity: UK only

blueprint · smart-ticketing-anomaly-log

Behind this dataset

Same schema. As many rows as you need.

These 120 rows came out of a blueprint — 19 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
  • Each row represents a single ticketing event flagged as anomalous.
  • Events must have a timestamp, transport line ID, anomaly type, and device ID.
  • Anomaly types include sensor malfunction, duplicate tap, fraudulent card, and location mismatch.
  • Include severity score (1-5) and resolution status (resolved/unresolved).
  • Events span multiple transport modes (bus, metro, tram).
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
smart-ticketing-anomaly-log

More in Transportation

Browse all
Also in TransportationUrban Transport Mode UsageFleet Energy Consumption MonitoringHourly Traffic Flow Time SeriesAll 1,967 datasets

What should your data show?

Preview 20 rows free
No signup. No card.