Machine Learning Course Applied to Motor Insurance
Online 300-hour course in machine learning applied to motor insurance. 6 modules covering Regulation (EU) 2024/1689 on artificial intelligence, Regulation (EU) 2016/679 (GDPR) and Python (scikit-learn). Dedicated tutor and enrolment open.
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 where machine learning adds value in motor insurance.
Prepare policy, vehicle and claims data for modelling.
Train pricing and risk selection models.
Build retention and customer value models.
Apply machine learning to claims management.
Compare machine learning models with GLMs and interpret results.
Deploy and govern a model in line with regulation.
Who it's for
- Motor insurance data scientist who wants to specialise in machine learning applied to motor insurance.
- Pricing actuary who wants to specialise in machine learning applied to motor insurance.
- MLOps engineer who wants to specialise in machine learning applied to motor insurance.
- Portfolio analyst who wants to specialise in machine learning applied to motor insurance.
- Claims analyst who wants to specialise in machine learning applied to motor insurance.
- Model risk manager who wants to specialise in machine learning applied to motor insurance.
- Engineering or science graduates looking to enter motor insurance.
What you'll work with
- Regulation (EU) 2024/1689 on artificial intelligence
- Regulation (EU) 2016/679 (GDPR)
- Directive 2004/113/EC (equal treatment in goods and services)
- ISO/IEC 23053 (framework for AI systems using machine learning)
- Royal Legislative Decree 8/2004 (motor vehicle insurance)
- Law 35/2015 (traffic compensation table)
- ISO/IEC 42001
6 modules · 300 h
1.1Value chain of the line: acquisition, pricing, policy, claim and renewal1.2Well-posed problems versus ill-posed problems1.3Data available at a motor insurer1.4External enrichment: vehicle, area and mobility1.5Business metric versus model metric1.6When a GLM is sufficient and when it is not1.7Cost of maintaining a model in production1.8Prioritising use cases by impact and feasibility1.9Data requirements for each use case1.10Workshop: prioritising use cases in an organisation
2.1Building the training set with time windows2.2Data leakage: the most common mistake2.3Vehicle variables: version, power, weight and equipment2.4Policyholder and regular driver variables2.5Geographic variables and their smoothing2.6Claims history and claim-free years2.7Encoding high-cardinality categorical variables2.8Missing values: imputation and indicator variables2.9Reusable feature store2.10Practice: preparing a dataset for pricing
3.1Gradient boosting for frequency and severity3.2Tweedie model and direct pure premium3.3Combining GLMs and tree models3.4Monotonic constraints and structured models3.5Interpretability: importance, partial dependence and local explanation3.6Prohibited variables and proxy detection3.7Impact analysis by customer groups3.8Validation and comparison with the current model3.9Phased deployment and measuring the effect3.10Practice: technical premium model and its validation
4.1Retention and cancellation prediction4.2Price elasticity and optimisation within ethical limits4.3Purchase propensity and cross-selling4.4Customer lifetime value4.5Customer segmentation with unsupervised methods4.6Preventing discrimination in commercial decisions4.7Controlled commercial trials4.8Measuring the incremental effect of an action4.9Regulatory limits on price optimisation4.10Practice: retention model and its responsible use
5.1Early claim classification and handler assignment5.2Prediction of final claim cost5.3Prediction of total loss and repairability5.4Repair cost estimation from photographs5.5Text processing of the claim report and the expert report5.6Prediction of litigation and duration5.7Detection of pre-existing damage5.8Automation of low-value payments and their controls5.9Effect on customer experience5.10Practice: final claim cost model
6.1Training and inference pipeline6.2Monitoring data drift and performance6.3Scheduled and controlled retraining6.4Version management and reproducibility6.5Model governance and owners by stage6.6Documentation for audit and for the supervisor6.7European artificial intelligence regulation applied to insurance6.8Training business teams6.9Common mistakes when industrialising models6.10Final project: complete use case, from data to production
How you'll learn
100 % online training on the SEIUM campus, with downloadable material, recorded classes and assigned technical tutor. No fixed timetables: students progress at their own pace within the intake, which makes it possible to combine study with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is Python (scikit-learn), XGBoost, H2O.ai, MLflow, R, in free, academic or evaluation versions. Tests are studied using real procedures for frequency models with gradient boosting, lapse and customer value models, and claims cost estimation with machine learning. Assessment is continuous by 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 where machine learning adds value in motor insurance.
Prepare policy, vehicle and claims data for modelling.
Train pricing and risk selection models.
Build retention and customer value models.
Apply machine learning to claims management.
Where this takes you
Requirements
- No prior degree required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient Spanish to follow technical regulatory reading.
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 is 300 hours in total spread over 3 to 5 months. That is between 10 and 15 hours per week on average, compatible with a full-time job.
The work is done with Python (scikit-learn), XGBoost, H2O.ai, MLflow, R. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
SEIUM's own 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 are credited towards the advanced programme. Check the credit transfer policy when you enrol.
Related programmes
Protection Coordination Course in MV/LV Networks
The Protection coordination course focuses on the design, implementation, and maintenance of electrical protection systems in medium and low voltage grids. This specialized Electrical Coordination training…
Course on Port Design in Urban Areas
The Course on Port Design in Urban Areas explores the planning, design, and development of port infrastructure in urban environments, integrating principles of urbanism, logistics, and…
Ethics in Deep Learning for ISR Course
Online 300-hour course in ethics in deep learning for ISR. 6 modules covering Additional Protocol I to the Geneva Conventions (arts. 36, 48 and 57), US…
More in Off-Road, Special Vehicles & Machinery
All Off-Road, Special Vehicles & Machinery programmes → · How to apply · Fees & financing · Scholarships