Course in Fraud Detection Through Telematics
300-hour online course in fraud detection through telematics. 6 modules covering Regulation (EU) 2016/679 (GDPR), Law 20/2015 (LOSSEAR, common anti-fraud files) and Python (scikit-learn). Assigned tutor and open enrolment.
Take the controls.
Run a real engineering trade-off from this programme. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Identify fraud typologies that can be detected through telematics.
Build signals and derived variables from driving data.
Train and evaluate fraud detection models.
Preserve digital evidence and assess its evidentiary value.
Manage false positives while ensuring fair treatment of the customer.
Implement and govern an anti-fraud system in compliance with regulations.
Develop a final telematics fraud detection project.
Who it's for
- Insurance fraud investigator who wants to specialise in fraud detection through telematics.
- Anti-fraud data scientist who wants to specialise in fraud detection through telematics.
- Telematics analyst who wants to specialise in fraud detection through telematics.
- Specialised claims handler who wants to specialise in fraud detection through telematics.
- IT forensic expert who wants to specialise in fraud detection through telematics.
- Fraud prevention manager who wants to specialise in fraud detection through telematics.
- Graduates in engineering or sciences seeking to enter motor insurance.
What you'll work with
- Regulation (EU) 2016/679 (GDPR)
- Law 20/2015 (LOSSEAR, common anti-fraud files)
- Regulation (EU) 2024/1689 (AI Act)
- Civil Procedure Act 1/2000 (evidence)
- ISO/IEC 27037 (digital evidence)
- Law 50/1980 on Insurance Contracts
- EDPB Guidelines 01/2020 on connected vehicles
6 modules · 300 h
1.1Typologies: staged, induced, exaggerated and backdated claims1.2Application fraud: falsified data and undeclared use1.3What a telematics device records and with what accuracy1.4Accelerometer, gyroscope, GPS and vehicle data1.5Reconstructing the sequence of an impact1.6Time and location footprint of a reported claim1.7Limitations of the data: sampling, signal loss and noise1.8What telematics cannot prove1.9Classic fraud indicators and their combination with the signal1.10Workshop: cross-checking a declaration against its telematics trail
2.1Pre-processing: filtering, resampling and drift correction2.2Event detection: harsh braking, cornering and collision2.3Estimating impact severity from the accelerometer2.4Impact direction and consistency with the damage2.5Speed profile before the incident2.6Trajectory and comparison with the declared route2.7Recognising the habitual driver from their pattern2.8Detection of undeclared professional use2.9Building variables for the model2.10Practice: extracting variables from a set of trips
3.1Expert rules: design, thresholds and maintenance3.2Supervised models on confirmed cases3.3The class imbalance problem and how to handle it3.4Appropriate metrics: precision, recall and cost of error3.5Anomaly detection without labels3.6Network analysis of involved parties3.7Combining rules and models in a decision engine3.8Prioritising claims by risk3.9Model drift and retraining3.10Practice: detection model with imbalanced data
4.1From the model alert to the claim investigation4.2Interviews and documentary cross-checking4.3Technical expert assessment supported by telematics data4.4Technical report: how to write it to be useful in court4.5Chain of custody of the data and its integrity4.6Admissibility of telematics evidence4.7Counter-expert opinion and defence of the insured4.8Legal limits: proportionality and data protection4.9Coordination with the legal team4.10Case study: backdated claim detected through a trip record
5.1The real cost of a false positive5.2Decision threshold and mandatory human review5.3Communication with the insured during the review5.4Complaints procedure and second opinion5.5Model bias and affected groups5.6Decision auditing and control sampling5.7Documentation of each decision taken5.8Reputational effect of an erroneous accusation5.9Quality indicators for the anti-fraud process5.10Practice: reviewing a batch of alerts with and without grounds
6.1Fitting the telematics anti-fraud engine into the claims process6.2Integration with management systems6.3Model governance and accountability for each decision6.4Compliance: customer information and legal basis6.5Sector collaboration and common files6.6Measuring the return on the anti-fraud programme6.7Training claims teams6.8Evolution of fraud and updating of signals6.9Common mistakes when deploying telematics detection6.10Final project: complete telematics anti-fraud programme
How you'll learn
100 % online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, which makes it possible to combine the course with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python (scikit-learn), FRISS, Neo4j, QGIS, SAS, in free, academic or evaluation versions. Tests are studied using real procedures for trajectory analysis and impact data, fraud scoring models, and review of cases with evidentiary value. Assessment is continuous per module, plus the final integrative project.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Identify fraud typologies that can be detected through telematics.
Build signals and derived variables from driving data.
Train and evaluate fraud detection models.
Preserve digital evidence and assess its evidentiary value.
Manage false positives while ensuring fair treatment of the customer.
Where this takes you
Requirements
- No previous qualification required.
- Internet connection and a computer capable of running the programme’s software.
- Sufficient command of Spanish to follow technical regulatory texts.
Ready to start?
Send your application today. Our admissions team replies within 72 hours with your study plan and funding options.
Frequently asked questions
The programme consists of 300 hours in total, spread over 3 to 5 months. That is between 10 and 15 hours a week on average, compatible with a full-time job.
The course uses Python (scikit-learn), FRISS, Neo4j, QGIS, SAS. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
An in-house SEIUM diploma upon passing the continuous assessment and the integrative project. It is in-house training, not an official qualification from the Ministry.
Yes. Modules passed in a course or postgraduate diploma in the same area can be recognised towards the advanced programme. Check the recognition policy when you enrol.
Related programmes
Course on Emerging Technologies in Remote Maintenance
Online course of 300 h in Emerging Technologies in Remote Maintenance. 6 modules covering ISO 17874 (remote handling devices for radioactive materials), IEC 61508 (functional safety)…
Personal branding course in motorsports
Personal Branding in Motorsport Course Explore building and managing a personal brand image for drivers, teams, and professionals in the motorsport world. It focuses on developing…
Course in Advanced Protection in Medium and Low Voltage
Online 300-hour course in advanced protection in medium and low voltage. 6 modules covering IEC 60255 (measuring and protection relays), IEEE 1584-2018 (arc flash hazard calculation)…
More in Nuclear Engineering & Nuclear Fuel Cycle Technologies
All Nuclear Engineering & Nuclear Fuel Cycle Technologies programmes → · How to apply · Fees & financing · Scholarships