Data Science Professional
European certification validating mastery of data science techniques: machine learning, statistical analysis, visualisation and deployment of predictive models in a professional environment.
Key skills
- ✓Develop and deploy supervised and unsupervised machine learning models
- ✓Analyse and visualise complex data with Python and SQL
- ✓Apply advanced statistical techniques and validate hypotheses
- ✓Put data pipelines and ML models into production
The question bank for this exam is prepared after your purchase. The exam is available no later than 48 hours after payment; you will receive an email as soon as it opens.
Is this right for you?
✓ This certification is right for you if:
- →Data analysts transitioning to data science
- →Python developers specialising in ML
- →Data consultants seeking European validation
- →BI professionals moving to predictive analytics
✗ This certification is not suitable if:
- →Beginners with no programming experience → direct yourself to PROVA Data Analytics Foundations (level 401)
- →Senior data scientists seeking an advanced certification → consult PROVA ML Engineering Master 801 or Fellow Series
Prerequisites & eligibility
Knowledge of Python and basic statistics required, no diploma condition.
Purchase options
Exam voucher, LMS pathway, bundle packs — build your order
Options d'achat
Composez votre parcours — voucher d'examen, préparation LMS, packs entreprise.
Skills assessed
ML modelling
Mastery of supervised, unsupervised algorithms and hyperparameter optimisation techniques.
Statistical analysis
Rigorous application of statistical tests, exploratory analysis and business hypothesis validation.
Production deployment
Putting models into production via REST API, Docker containerisation and performance monitoring.
Data communication
Creating impactful visualisations and communicating insights to non-technical stakeholders.
Exam format
Curriculum
Statistical fundamentals and data exploration
Descriptive statistics (mean, median, variance, standard deviation), distributions (normal, binomial, Poisson), confidence intervals, hypothesis testing (t-test, chi2, ANOVA), p-value and significance. Exploratory data analysis (EDA): univariate and bivariate visualisations, correlation matrices, outlier detection (IQR, Z-score), handling missing values (imputation, deletion). Feature engineering: variable creation, encoding (one-hot, label encoding), normalisation and standardisation, binning.
Supervised and unsupervised Machine Learning
Supervised learning: simple and multiple linear regression, logistic regression, decision trees (CART), random forests, gradient boosting (XGBoost, LightGBM, CatBoost), Support Vector Machines (SVM), k-nearest neighbors (KNN). Unsupervised learning: clustering (k-means, hierarchical clustering, DBSCAN), dimensionality reduction (PCA, SVD, t-SNE, UMAP), anomaly detection. Fundamental concepts: bias-variance tradeoff, curse of dimensionality, distance metrics.
Model validation and optimisation
Validation techniques: train/test split, k-fold cross-validation, stratified sampling, temporal validation for time series. Performance metrics: classification (accuracy, precision, recall, F1-score, AUC-ROC, confusion matrix), regression (MSE, RMSE, MAE, R²). Diagnostics: overfitting, underfitting, learning curves. Optimisation: L1 (Lasso) and L2 (Ridge) regularisation, ElasticNet, grid search, random search, Bayesian optimisation. Feature selection: variable importance, recursive feature elimination, SHAP analysis.
Deployment and production
Scikit-learn pipelines: transformers, estimators, Pipeline and ColumnTransformer. Model serialisation: pickle, joblib, ONNX. Creating REST APIs: Flask, FastAPI, prediction endpoints. Containerisation: Docker basics, Dockerfile for ML applications. MLOps: model versioning (MLflow basics), monitoring performance in production, drift detection, A/B testing of models. Best practices: reproducibility, logging, dependency management.
How to fund your certification
3 ways to cover the cost of your certification
OPCO — Employer funding
Ask your employer to cover the cost through your OPCO (employee training plan).
Personal — €450 incl. VAT
Secure online payment by credit card (Stripe).
Business rate: €585 excl. VAT
Business — custom quote
Teams, cohorts or private catalogue: a quote tailored to your volumes and goals.
Frequently asked questions
Which programming languages are covered?
The exam focuses mainly on Python (pandas, numpy, scikit-learn, matplotlib). SQL is also assessed for data manipulation. Concepts are language-agnostic but practical examples use the standard Python ecosystem in data science.
Is coding required during the exam?
You will need to read, understand and identify errors in code, but not write full code from scratch. The emphasis is on conceptual and methodological understanding.
Is deep learning on the syllabus?
This Standard level certification covers the fundamentals of classical machine learning. Deep learning (neural networks, CNN, RNN) is addressed conceptually but is not the main objective. For a deep learning specialisation, consult our Master 801 certifications in AI Engineering.
Can I use documentation during the exam?
No, the exam is closed-book. You must master the concepts, algorithms and methodologies without external assistance. This ensures the certification reflects your real skills deployable in a professional situation.
Your certification pathway
Before, during, after — the recommended progression
Droits du candidat
Transparence
Les critères de décision et le barème sont documentés et accessibles avant l'examen.
Droit d'appel
Toute décision peut être contestée dans les 30 jours. Examen par un tiers indépendant.
Plainte
Toute personne peut signaler un dysfonctionnement. Formulaire public accessible sans compte.
