Diploma in Explainable AI Applied to Fraud Prevention
Online postgraduate diploma of 800 hours in explainable AI applied to fraud prevention. 8 modules covering fraud typologies, predictive fraud models, global and local explainability, fairness and bias, the EU AI regulatory framework and model governance, with an assigned technical tutor.
Diploma in Explainable AI Applied to Fraud Prevention — studying from New Zealand
Off-road and special vehicle engineering is a major strength in New Zealand, reflecting the importance of agriculture, forestry, mining and construction. Manufacturers and fabricators in the Waikato and Canterbury produce tractors, harvesters, dairy equipment and specialised machinery, many of which are exported worldwide. Engineers in this field work on design, testing and safety compliance for equipment used on farms, in plantations and on remote worksites.
Fees for New Zealand: NZ$2,960 (New Zealand dollar), with instalments and employer sponsorship available.
Relevant bodies in New Zealand
Typical roles
Questions from New Zealand
Which New Zealand bodies relate to off-road and specialist vehicle engineering?
Engineering New Zealand is the main professional body, and vehicle compliance is handled by the NZ Transport Agency Waka Kotahi. Heavy machinery and certain specialist vehicles can also fall under WorkSafe New Zealand rules. SEIUM's qualifications are private and not accredited by any national body, so employers and regulators decide their value.
Who hires off-road and special vehicle engineers in New Zealand?
Employers include forestry and agricultural equipment firms, mining and civil construction contractors, fabrication shops, and emergency or utility vehicle fleets. Practical design, safety and maintenance skills are central to hiring. A SEIUM qualification may help, but its weight depends on the employer.
How does the study load work for someone with a job here?
The programme is fully online, so you can study around work from anywhere in New Zealand without a student visa. Specialist courses take 300 hours, postgraduate diplomas 800 hours and master's programmes 1,900 hours. You get an assigned technical tutor, and fees can be paid in instalments or sponsored by an employer.
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
Understand fraud typologies and the detection cycle.
Build robust predictive fraud models.
Apply global and local explainability techniques.
Assess and mitigate bias in models.
Comply with the European artificial intelligence regulatory framework.
Govern models in production.
Develop an explainable fraud detection system.
Who it's for
- Fraud data scientists
- Responsible AI specialists
- Fraud analysts
- Model auditors
- AI compliance officers
- MLOps engineers
- Engineering or science graduates looking to move into insurance
What you'll work with
- Regulation (EU) 2024/1689 (EU Artificial Intelligence Act)
- Regulation (EU) 2016/679 (GDPR) (protection of personal data)
- ISO/IEC 42001:2023 (AI management systems)
- ISO/IEC 23894:2023 (AI risk management)
- Law 10/2010 (Spanish anti-money laundering act)
- NIST AI Risk Management Framework 1.0 (AI risk management)
- Law 50/1980 (Spanish Insurance Contract Act)
- Python with scikit-learn
- SHAP
- LIME
- MLflow
- XGBoost
8 modules
1.1Typologies of claims fraud1.2Underwriting and payment fraud1.3Organised versus opportunistic fraud1.4The cost of fraud to the sector1.5The detection and investigation cycle1.6Data sources for detection1.7Classic red-flag indicators1.8Rule-based systems versus models1.9Industry databases1.10Workshop: catalogue of fraud patterns
2.1Data and feature preparation2.2Imbalanced classes and resampling2.3Logistic regression2.4Trees, random forests and gradient boosting2.5Anomaly detection with isolation forest2.6Text models on claim descriptions2.7Temporal validation2.8Cost-oriented metrics2.9Thresholds and investigation capacity2.10Practical exercise: fraud model with scikit-learn
3.1Intrinsic and post hoc interpretability3.2Permutation feature importance3.3Partial dependence and ICE3.4Global surrogate models3.5Rules extracted from models3.6Explainable generalised additive models3.7Comparison between methods3.8Limitations of explainability3.9Model documentation3.10Lab: global explanation of a boosting model
4.1SHAP values and game theory4.2LIME and local approximations4.3Counterfactual explanations4.4Anchors and local rules4.5Explanations for investigators4.6Explanations for customers4.7Stability and fidelity4.8Explainability in fraud graphs4.9Visualising explanations4.10Practical exercise: SHAP report on a suspicious claim
5.1Sources of bias in historical data5.2Protected and proxy variables5.3Fairness metrics5.4Pre-, in- and post-processing mitigation5.5Trade-offs between accuracy and fairness5.6Bias auditing5.7Impact on vulnerable groups5.8Documenting decisions5.9Human review5.10Case study: bias audit of a model
6.1Regulation (EU) 2024/1689 on artificial intelligence6.2High-risk systems in insurance6.3Article 22 of the GDPR6.4Right to explanation and transparency6.5Law 10/2010 and financial fraud6.6ISO/IEC 42001 AI management6.7ISO/IEC 23894 AI risk management6.8EIOPA guidance on AI6.9Provider and deployer responsibilities6.10Workshop: conformity assessment of an AI system
7.1Deployment to production7.2Drift monitoring7.3Retraining and version control7.4MLOps with MLflow7.5Decision logging7.6Investigator feedback loop7.7Model incident management7.8Model governance committees7.9Internal audit7.10Practical exercise: monitoring plan for a model
8.1Definition of the fraud case8.2Data preparation8.3Model training8.4Global and local explanations8.5Fairness analysis8.6Regulatory assessment8.7Deployment and governance plan8.8Conclusions8.9Report and presentation8.10Final project: final review with your tutor
How you'll learn
100% online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. There are no fixed timetables: you progress at your own pace within each intake, so it is compatible with work.
Each module combines theory, guided reading of the original regulations and applied exercises. The working software is Python with scikit-learn, SHAP, LIME, MLflow and XGBoost, in free, academic or evaluation versions. Cases are studied on real procedures for detecting suspicious claims with explainable models, auditing bias in fraud models and preparing regulatory documentation for AI systems. Assessment is continuous by module plus the final project.
Standards covered: Regulation (EU) 2024/1689, Regulation (EU) 2016/679 (GDPR), ISO/IEC 42001:2023, ISO/IEC 23894:2023, Law 10/2010, NIST AI Risk Management Framework 1.0, Law 50/1980.
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
- Prior technical training or professional experience in the sector. No university degree is required.
- An internet connection and a computer able to run 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 800 hours over 6–8 months. You set your own pace within each intake, and your tutor helps you plan the workload around your job.
You work with Python with scikit-learn, SHAP, LIME, MLflow, XGBoost, 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 final project. 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 are recognised in a higher programme in the same area (postgraduate diploma or master's). Ask about the recognition policy when you enrol.
Prior technical training or professional experience in the sector (no university degree required), a computer able to run the software 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
Postgraduate Diploma in H₂ Validation and Global Regulations
Online 800-hour Postgraduate Diploma in H₂ Validation and Global Regulations. 8 modules covering UNECE Regulation No. 134 (hydrogen vehicles), GTR No. 13 (global technical regulation for…
Postgraduate Diploma in Mixed-Terrain Dynamics and Control
Online 800 h Postgraduate Diploma in Mixed-Terrain Dynamics and Control. 8 modules covering ISO 8855 (vehicle dynamics: vocabulary), ISO 3888-2 (obstacle avoidance manoeuvre) and MATLAB/Simulink. Assigned…
Diploma in Off-Highway Inverters and Power Electronics
Online postgraduate diploma of 800 hours in inverters and power electronics for off-highway machinery. 8 modules covering power semiconductors including SiC and GaN, inverter topologies, electric…
More in Off-Road, Special Vehicles & Machinery
All Off-Road, Special Vehicles & Machinery programmes → · How to apply · Fees & financing · Scholarships