Master’s in Actuarial, Telematics & Data Engineering
Online master's programme of 1,900 hours in actuarial, telematics and data engineering, structured in 12 modules covering non-life actuarial mathematics, telematics data, driving feature engineering, GLMs, machine learning, data platforms, usage-based insurance, geospatial risk, data-driven claims, regulation and solvency, with an assigned technical tutor.
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
Apply non-life actuarial mathematics to premium and reserve calculation.
Design risk variables from driving telematics data.
Build GLM and machine learning models for ratemaking.
Develop scalable data architectures for large telematics volumes.
Design profitable and transparent usage-based insurance products.
Assess compliance of pricing models with the GDPR and AI regulation.
Integrate analytical results into the insurer's solvency management.
Who it's for
- Pricing actuaries.
- Data scientists working in insurance.
- Telematics analysts.
- Pricing managers.
- Actuarial data engineers.
- Usage-based insurance consultants.
- Engineering or science graduates seeking to enter motor insurance.
What you'll work with
- Directive 2009/138/EC (Solvency II) (EU prudential regime for insurers)
- IFRS 17 (insurance contracts)
- Regulation (EU) 2016/679 (GDPR) (data protection)
- Regulation (EU) 2024/1689 (artificial intelligence)
- Directive (EU) 2016/97 (IDD) (insurance distribution)
- Law 50/1980 on Insurance Contracts (Spanish insurance contract law)
- ISO/IEC 27001:2022 (information security management)
- Regulation (EU) 2015/758 (eCall)
- R
- Python (scikit-learn, LightGBM)
- Apache Spark
- QGIS
- SAS
12 modules · 1900 h
1.1Frequency and severity random variables1.2Poisson, negative binomial and Pascal distributions1.3Severity distributions: lognormal, gamma and Pareto1.4Collective risk model and Panjer's formula1.5Pure premium, safety loadings and expenses1.6Premium calculation principles1.7Bühlmann credibility theory1.8Claims development triangles1.9Chain-Ladder and Bornhuetter-Ferguson methods1.10Workshop: IBNR reserving with real triangles
2.1Architecture of a fleet telematics solution2.2OBD-II devices, black boxes and smartphones2.3CAN bus and the SAE J1939 protocol2.4GNSS, accelerometer and gyroscope signals2.5Sampling frequency and signal quality2.6Data ingestion with MQTT and message queues2.7Time-series storage2.8Consent and transparency with the driver2.9Deployment costs and business models2.10Laboratory: decoding a vehicle's CAN frames
3.1Trip detection and journey segmentation3.2Map matching on road networks3.3Harsh braking, acceleration and cornering events3.4Speeding relative to the legal limit3.5Night-time driving and exposure by time band3.6Mobile phone use while driving3.7Exposure indicators: kilometres, hours, trips3.8Aggregation by driver, vehicle and policy3.9Handling outliers and noise3.10Practical exercise: building a driving score
4.1Exponential family and link functions4.2Poisson GLM for frequency with exposure offset4.3Gamma GLM for average cost4.4Tweedie model for total cost4.5Variable selection and AIC/BIC criteria4.6Interactions and smoothing of continuous variables4.7Validation: lift charts and Lorenz curves4.8Actuarial Gini index4.9Comparison of current and proposed tariffs4.10Case study: motor third-party liability tariff
5.1Decision trees and random forests5.2Gradient boosting with XGBoost and LightGBM5.3Poisson and Tweedie loss functions5.4Time-based cross-validation5.5Hyperparameter tuning5.6Monotonicity and business constraints5.7Explainability with SHAP and partial dependence5.8GAMs and hybrid GLM-ML models5.9Overfitting risk and temporal stability5.10Laboratory: frequency model with gradient boosting
6.1Data lake and data warehouse in insurers6.2Lakehouse architecture and Delta/Parquet formats6.3Distributed processing with Spark6.4ETL/ELT pipelines and orchestration6.5Dimensional modelling of policies and claims6.6Data catalogue and lineage6.7Data quality: rules and monitoring6.8Integration with core policy systems6.9Cloud costs and optimisation6.10Practical exercise: telematics data pipeline in Spark
7.1Pay As You Drive and Pay How You Drive7.2Per-kilometre and per-minute insurance7.3Discount and bonus programmes7.4Insurance for fleets and shared vehicles7.5Covers for personal mobility and e-scooters7.6Designing the customer value proposition7.7Adverse selection and self-selection risks7.8Retention and renewal in UBI products7.9Profitability analysis by cohort7.10Case study: launching a PAYD product
8.1Reference systems and projections8.2Geocoding of risk addresses8.3Claims maps by zone8.4Road risk indices by road segment8.5Spatial statistics and autocorrelation8.6Open traffic and accident data8.7Rating zones8.8Visualisation with QGIS and Python libraries8.9Territorial bias and fairness8.10Workshop: risk zoning from claims data
9.1Accident notification from telematics9.2Accident reconstruction with vehicle data9.3eCall and automatic emergency alerts9.4Automatic claims triage9.5Early claim cost estimation9.6Fraud detection with telematics signals9.7Workshop analytics and repair times9.8Recoveries and liability between insurers9.9Customer experience indicators9.10Practical exercise: reconstructing a claim with GNSS data
10.1Processing location data under the GDPR10.2Legal bases and impact assessments10.3Pseudonymisation and anonymisation10.4Price discrimination and prohibited variables10.5Algorithmic fairness in pricing10.6Requirements of the EU AI Act10.7Product governance under the IDD10.8Transparency and the right to explanation10.9Information security in telematics10.10Case study: impact assessment of a UBI programme
11.1Pillars of Solvency II11.2Best estimate and risk margin11.3Non-life solvency capital requirement11.4Premium and reserve risk11.5ORSA and risk appetite11.6Accounting measurement under IFRS 1711.7Reinsurance as a capital tool11.8Stress testing of motor portfolios11.9Actuarial function and internal control11.10Workshop: simplified premium and reserve risk SCR calculation
12.1Definition of the actuarial problem and scope12.2Literature and state-of-the-art review12.3Data selection and preparation12.4Model and validation design12.5Development of the analytical solution12.6Evaluation of results and sensitivity12.7Business and solvency impact12.8Ethical and regulatory considerations12.9Thesis report12.10Master's Thesis: defence before a panel
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 the intake, so the programme can be combined with work.
Each module combines theory, guided reading of the original standard and applied exercises. The working software is R, Python (scikit-learn, LightGBM), Apache Spark, QGIS and SAS, in free, academic or evaluation versions. Testing is studied through real procedures for pricing a motor portfolio with telematics data, reserving claims with development triangles and validating driving score models. Assessment is continuous by module, plus the final Master's Thesis.
Standards covered: Directive 2009/138/EC (Solvency II), IFRS 17, Regulation (EU) 2016/679 (GDPR), Regulation (EU) 2024/1689, Directive (EU) 2016/97 (IDD), Law 50/1980 on Insurance Contracts, ISO/IEC 27001:2022, Regulation (EU) 2015/758.
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's 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 R, Python (scikit-learn, LightGBM), Apache Spark, QGIS and SAS, 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), 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
Master’s in Telematics and Actuarial Pricing of Connected Mobility Engineering
Online master's programme of 1,900 hours in telematics and actuarial pricing engineering for connected mobility, structured in 12 modules covering connected vehicle data, insurance price theory,…
Master’s in Aviation and Airport Insurance Engineering
Online master's programme of 1,900 hours in Aviation and Airport Insurance Engineering. 12 modules covering aircraft risk, aviation regulation, aviation liability, aviation hull, airport insurance and…
Master’s in Global Insurance Compliance Engineering (EU/UK, US/Canada, LATAM, APAC, MENA/Africa)
Online master's programme of 1,900 hours in global insurance compliance engineering (EU/UK, US/Canada, LATAM, APAC, MENA/Africa): 12 modules covering international insurance programmes, regional regulatory frameworks, sanctions,…
More in Insurance, Risk & Actuarial Data
All Insurance, Risk & Actuarial Data programmes → · How to apply · Fees & financing · Scholarships