Big Data Course in Road Accident Prediction
Online 300-hour course in Big Data for road accident prediction. 6 modules covering ISO 39001 (road safety management), Directive 2008/96/EC (road infrastructure safety) and Apache Spark. Personal tutor assigned 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
Describe road accident data sources and their units of analysis.
Integrate large volumes of traffic, weather, infrastructure and collision data.
Identify black spots and concentration sections through spatial analysis.
Train and validate predictive models of accident frequency and severity.
Translate predictions into prioritised road safety measures.
Apply ethical and data protection criteria in the use of predictive models.
Develop an accident prediction project on a real road network.
Who it's for
- Road safety data scientist who wants to specialise in Big Data for road accident prediction.
- Traffic engineer who wants to specialise in Big Data for road accident prediction.
- Geospatial analyst who wants to specialise in Big Data for road accident prediction.
- Road safety observatory technician who wants to specialise in Big Data for road accident prediction.
- Accident analyst at insurance companies who wants to specialise in Big Data for road accident prediction.
- Urban mobility consultant who wants to specialise in Big Data for road accident prediction.
- Graduates in engineering or sciences seeking to join traffic authorities.
What you'll work with
- ISO 39001 (road safety management)
- Directive 2008/96/EC (road infrastructure safety)
- Directive (EU) 2019/1936 (amendment on road infrastructure safety management)
- Royal Legislative Decree 6/2015 (Road Traffic Law)
- Order INT/2223/2014 (National Register of Road Traffic Casualties)
- Regulation (EU) 2016/679 (GDPR)
- Regulation (EU) 2024/1689 (AI Act)
6 modules · 300 h
1.1Accident, victim, vehicle and involved person1.2Official sources: police reports, statistics and hospital records1.3Traffic data: traffic counts, average speed and composition1.4Infrastructure data: alignment, pavement and signage1.5Vehicle data and safety equipment1.6Weather and lighting data1.7Mobile phone and mobility app data1.8Under-reporting of accidents without casualties1.9Unit of analysis: section, intersection, trip or person1.10Workshop: inventory of sources for a metropolitan area
2.1Architecture for large-scale mobility data2.2Distributed processing and batch computing2.3Streaming data and time windows2.4Spatial linking of accidents to the road network2.5Reference systems, projections and geocoding errors2.6Temporal matching between sources2.7Anonymisation of travel data2.8Data quality and consistency checks2.9Platform cost and optimisation2.10Practical: integration of three heterogeneous sources
3.1Accident density and spatial smoothing3.2Statistical identification of concentrations3.3Regression to the mean and false black spots3.4Poisson models with spatial effects3.5Exposure by section and comparable rates3.6Comparison between similar sections3.7Risk maps and their responsible interpretation3.8Prioritising interventions by section3.9Evaluating the effect of an improvement scheme3.10Practical: detection of concentrations on a real network
4.1Prediction by section, by hour and by conditions4.2Count models and machine learning models4.3Leading variables: traffic, weather and events4.4Prediction of injury severity4.5Risk models by user type: pedestrian, cyclist and driver4.6Time series and long-term trends4.7Spatial and temporal validation4.8Interpretability and communication to the road manager4.9Limits of predicting rare events4.10Practical: accident model by section and time slot
5.1Vision Zero and road safety frameworks5.2Infrastructure measures and their expected effect5.3Speed management and traffic-calmed zones5.4Protection of vulnerable road users5.5Campaigns and enforcement: where and when5.6Impact assessment of measures adopted5.7Cost-benefit analysis of interventions5.8Communicating results to the administration5.9Use of the models by insurers and managers5.10Practical: prioritised action plan
6.1Privacy in large-scale mobility data6.2Re-identification risk and protective measures6.3Territorial equity in prioritising interventions6.4Transparency of models used by the administration6.5Open data and reproducibility of analyses6.6Data governance across administrations6.7Documentation and auditing of models6.8Common errors in accident analysis6.9Public communication of casualty figures6.10Final project: complete accident study of a road network
How you'll learn
100 % online training on the SEIUM campus, with downloadable material, recorded classes and an assigned technical tutor. No fixed timetable: 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 software used is Apache Spark, Python (GeoPandas), QGIS, R, Tableau, in free, academic or evaluation versions. Case studies cover real procedures for detecting accident concentration sections, accident prediction models using open data, and evaluation of road safety measures. 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.
Describe road accident data sources and their units of analysis.
Integrate large volumes of traffic, weather, infrastructure and collision data.
Identify black spots and concentration sections through spatial analysis.
Train and validate predictive models of accident frequency and severity.
Translate predictions into prioritised road safety measures.
Where this takes you
Requirements
- No prior degree required.
- Internet connection and a computer capable of running the programme's software.
- Sufficient level 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 comprises 300 hours in total, spread over 3 to 5 months. That is an average of 10 to 15 hours per week, compatible with a full-time job.
The course uses Apache Spark, Python (GeoPandas), QGIS, R and Tableau. Free, academic or evaluation versions are used, and the tutor indicates the free alternative where one exists.
A SEIUM 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 recognised in the advanced programme. Check the recognition policy when you enrol.
Related programmes
ISO/IEC Course in Embedded Avionics
300-hour online course in ISO/IEC in embedded avionics. 6 modules covering DO-178C (software in airborne systems), DO-254 (complex electronic hardware) and Ansys SCADE Suite. Assigned tutor…
Air traffic demand forecasting course
The Air Traffic Demand Forecasting Course focuses on the analysis and forecasting of passenger and cargo demand. It covers the use of econometric models, time series…
International Regulation in Reactor Design Course
Online 300-hour course in international regulation in reactor design. 6 modules covering IAEA SSR-2/1 (Rev.1) (Safety of Nuclear Power Plants: Design), IAEA SSG-2 (Rev.1) (Deterministic Safety…
More in Regulation, Safety, RAMS & Homologation
All Regulation, Safety, RAMS & Homologation programmes → · How to apply · Fees & financing · Scholarships