Master’s in Fraud, Anomalies and Advanced Detection in Mobility Insurance Engineering
Online master's programme of 1,900 hours in Fraud, Anomaly and Advanced Detection Engineering in Mobility Insurance. 12 modules covering fraud typologies, detection data, anomaly statistics, supervised and unsupervised learning, network and graph analysis, telematics, text and image forensics, SIU investigation and the legal framework, with an assigned technical tutor.
Master’s in Fraud, Anomalies and Advanced Detection in Mobility Insurance Engineering — studying from New Zealand
New Zealand's insurance and financial services sector is concentrated in Auckland and Wellington, with a strong focus on general insurance, life insurance and risk management. Natural hazard risk, particularly from earthquakes, is a major consideration, and the Earthquake Commission provides residential natural disaster cover. Actuarial and risk data professionals work for insurers, reinsurers, regulators and consultancies, with oversight from the Reserve Bank of New Zealand and the Financial Markets Authority.
Fees for New Zealand: NZ$15,700 (New Zealand dollar), with instalments and employer sponsorship available.
Relevant bodies in New Zealand
Typical roles
Questions from New Zealand
Which New Zealand bodies recognise actuarial and risk qualifications?
The Actuarial Society of New Zealand and the New Zealand Institute of Actuaries work alongside international bodies such as the Institute and Faculty of Actuaries. Membership and professional credentials in these fields are set by those bodies, not by private providers. SEIUM's qualifications are private and not accredited by any national body, so their standing depends on how your employer or the relevant body assesses them.
Do insurers and financial firms in New Zealand hire people with data and risk skills?
New Zealand's insurance, banking and government sectors do employ people in risk, pricing and data analysis, and the Reserve Bank and insurers both draw on these skills. Hiring usually depends on demonstrated technical ability and professional credentials. A SEIUM qualification can support your application, but whether it is valued is up to each employer.
How is the programme delivered and paid for?
The programme is 100% online and taught in English, so no student visa is needed to study from New Zealand. You are assigned a technical tutor and complete a final project. Fees are payable in instalments, and employer sponsorship is possible. Time commitment varies by programme, from 300 hours for specialist courses to 1,900 hours for master's programmes.
Take the controls.
Run a real engineering trade-off from this field. Move the sliders, watch the model react in real time and beat the challenge.
What you will be able to do
Identify the main fraud typologies in mobility insurance.
Integrate data sources for anomaly detection.
Develop supervised and unsupervised fraud detection models.
Apply graph analysis to dismantle organised fraud networks.
Use telematics data and images as technical evidence.
Organise investigation units in line with the legal framework.
Measure the economic impact of an anti-fraud strategy.
Who it's for
- Anti-fraud analysts who want to move from rules to advanced detection models.
- SIU claims investigators looking to work with data, graphs and digital evidence.
- Data scientists building anomaly and fraud detection systems for insurers.
- Heads of investigation units responsible for strategy and results.
- Motor loss adjusters who want to strengthen their technical fraud analysis.
- Fraud prevention consultants advising insurers and mobility operators.
- Engineering or science graduates aiming to enter motor insurance.
What you'll work with
- Regulation (EU) 2016/679 (GDPR: personal data protection)
- Organic Law 3/2018 (Spanish data protection and digital rights law)
- Organic Law 10/1995 (Spanish Criminal Code, including insurance fraud)
- Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
- Law 20/2015 (LOSSEAR: regulation, supervision and solvency of insurers)
- Law 5/2014 (Spanish Private Security Act)
- ISO/IEC 27037:2012 (identification, collection and preservation of digital evidence)
- Neo4j
- Python (scikit-learn, PyOD)
- SAS Fraud Management
- Shift Technology
- i2 Analyst's Notebook
12 modules · 1900 h
1.1Typology of motor insurance fraud1.2Opportunistic versus organised fraud1.3Staged and induced accidents1.4Inflation of damage and injuries1.5Fraud at policy inception1.6Internal and supplier fraud1.7Fraud in shared mobility1.8Economic impact of fraud1.9Classic red-flag indicators1.10Case study: analysis of an organised fraud file
2.1Policy, claims and payment data2.2Accident telematics data2.3Shared industry databases2.4Open sources and OSINT2.5Repair shop and loss adjuster data2.6Injury and medical centre data2.7Data quality and entity de-duplication2.8Entity resolution2.9Integration of unstructured data2.10Practical exercise: entity resolution in a claims file
3.1Definition of anomaly and outlier3.2Univariate and robust methods3.3Mahalanobis distance3.4Benford's law3.5Time-series analysis of claims3.6Detection of structural breaks3.7Density models3.8Statistical tests for patterns3.9False positive rate3.10Lab: applying Benford's law to repair amounts
4.1Case labelling and investigation bias4.2Imbalanced classes and resampling4.3Baseline logistic regression4.4Gradient boosting for fraud4.5Metrics: precision, recall and PR curve4.6Cost-based threshold tuning4.7Explainability for investigators4.8Feedback of investigation outcomes4.9Drift of adaptive fraud4.10Practical exercise: suspicion scoring model
5.1Isolation Forest5.2Local Outlier Factor5.3Autoencoders for anomalies5.4Claims clustering5.5One-class SVM5.6Combining detectors5.7Evaluation without labels5.8Semi-supervised learning5.9Active learning with investigators5.10Lab: autoencoder on property damage claims
6.1Graph theory applied to fraud6.2Building the claims graph6.3Centrality measures6.4Community detection6.5Fraud ring patterns6.6Graph databases6.7Graph neural networks6.8Network visualisation6.9Temporal network analysis6.10Case study: identifying a fraud network with Neo4j
7.1Verification of accident time and location7.2Impact profile with accelerometers7.3Consistency between damage and impact force7.4Detection of staged accidents7.5Tampering with telematics devices7.6Mileage fraud in usage-based products7.7Connected vehicle data7.8Chain of custody of telematics data7.9Evidentiary value in court7.10Practical exercise: verifying a claim with impact data
8.1Natural language processing of statements8.2Entity extraction from reports8.3Detection of duplicate texts8.4Language models to summarise case files8.5Forensic analysis of photographs8.6EXIF metadata and image manipulation8.7Detection of AI-generated images8.8Reuse of photos across claims8.9Forged documents8.10Lab: detection of reused images
9.1Organisation of an investigation unit9.2Alert prioritisation9.3Investigation procedures9.4Interviews and statements9.5Working with private investigators9.6Digital evidence and its preservation9.7Coordination with law enforcement9.8Criminal complaints and court proceedings9.9Recoveries and civil actions9.10Case study: investigation plan for a suspicious claim
10.1Insurance fraud in the Spanish Criminal Code10.2GDPR and processing for anti-fraud purposes10.3Common insurance industry databases10.4Automated decisions and human oversight10.5The AI Act and assessment systems10.6Rights of the policyholder10.7Private security and Law 5/201410.8Anti-money laundering10.9Bias and discrimination in detection10.10Workshop: impact assessment of an anti-fraud system
11.1Corporate anti-fraud strategy11.2Calculating return on investment11.3Indicators: detection rate and savings11.4Balancing fraud control and customer experience11.5Deterrence and prevention at policy inception11.6Industry collaboration11.7Management of technology providers11.8Implementation in claims systems11.9Continuous improvement11.10Practical exercise: anti-fraud dashboard
12.1Definition of the type of fraud to address12.2State-of-the-art review12.3Data preparation and anonymisation12.4Design of the detection architecture12.5Model development12.6Evaluation with business metrics12.7Integration into the investigation process12.8Legal and ethical analysis12.9Master's Thesis report12.10Master's Thesis: defence before a panel
How you'll learn
100% online training on the SEIUM campus, with downloadable materials, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so the programme is compatible with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Neo4j, Python (scikit-learn, PyOD), SAS Fraud Management, Shift Technology and i2 Analyst's Notebook, in free, academic or evaluation versions. Exercises are based on real procedures: detection of organised fraud networks using graphs, claims verification with telematics impact data, and forensic analysis of images submitted with claims. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: Regulation (EU) 2016/679 (GDPR), Organic Law 3/2018 on Data Protection and Guarantee of Digital Rights, Organic Law 10/1995 of the Criminal Code, Regulation (EU) 2024/1689 on Artificial Intelligence, Law 20/2015 (LOSSEAR), Law 5/2014 on Private Security and ISO/IEC 27037:2012.
Build it end to end
Your final project follows the real engineering workflow, step by step, reviewed by your tutor.
Where this takes you
Requirements
- University degree in engineering, science or architecture, or equivalent demonstrable professional experience.
- Internet connection and a computer capable of running the programme software.
- English sufficient to read technical standards.
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 totals 1,900 hours over 12–14 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with Neo4j, Python (scikit-learn, PyOD), SAS Fraud Management, Shift Technology and i2 Analyst's Notebook, using free, academic or evaluation versions. Your tutor indicates the free alternative wherever one exists.
A SEIUM Institute diploma, awarded on passing the continuous assessment and the Master's Thesis. It is SEIUM's own qualification, not an official state degree; its recognition depends on the programme completed and the regulations of each country.
Yes. Modules passed in a course or postgraduate diploma in the same area are recognised in the higher programme. Ask about the recognition policy when you enrol.
A university degree in engineering, science or architecture, or equivalent professional experience, plus a suitable computer and English sufficient to read technical standards.
Start dates are set by SEIUM's faculty for each intake. Our admissions team will confirm the next available date when you apply.
Related programmes
Master’s in Geospatial Analytics and Remote Sensing for Risk and Claims Engineering
Online master's programme of 1,900 hours in Geospatial Analytics and Remote Sensing Engineering for Risk and Claims. 12 modules covering geographic information for insurance, remote sensing,…
Master’s in Health and Performance Actuarial Engineering for Athletes and Driver Fleets
Online master's programme of 1,900 hours in Health and Performance Actuarial Engineering for Athletes and Driver Fleets. 12 modules covering personal insurance and health risk, sports…
Master’s in Compliance, Solvency & International Regulation Engineering
Online master's programme of 1,900 hours in Compliance, Solvency & International Regulation Engineering, structured in 12 modules covering insurance regulatory architecture, the three pillars of Solvency…
More in Insurance, Risk & Actuarial Data
All Insurance, Risk & Actuarial Data programmes → · How to apply · Fees & financing · Scholarships