Machine Learning Associate
Certify your skills in Machine Learning: data preparation, supervised and unsupervised modelling, evaluation and deployment of models in a production environment.
Key skills
- ✓Preprocessing and feature engineering
- ✓Implementation of supervised and unsupervised algorithms
- ✓Evaluation and optimisation of ML models
- ✓Deployment and monitoring of models in 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 Machine Learning
- →Python Developers wishing to specialise in ML
- →Data engineers validating their operational skills
✗ This certification is not suitable if:
- →Programming beginners without a Python base: first consider a Python Data Analysis training before tackling Machine Learning.
- →ML experts seeking an advanced certification in Deep Learning or MLOps: please consult our Master 801 certifications in Deep Learning Engineering or MLOps Architect instead.
Prerequisites & eligibility
Online registration, payment by credit card or bank transfer, immediate access to the preparation LMS.
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
Advanced modelling
Mastery of classification, regression, clustering and dimensionality reduction algorithms with scikit-learn and modern frameworks.
Robust ML pipeline
Construction of end-to-end pipelines including cross-validation, hyperparameter tuning and management of imbalanced data.
Production deployment
Putting models into production via REST API, Docker containerisation and real-time performance monitoring.
Feature engineering
Transformation and selection of variables, categorical encoding, normalisation and advanced management of missing data.
Exam format
Curriculum
Data preparation and exploration
Data cleaning techniques (missing values, duplicates, inconsistencies). Feature engineering: variable creation, encoding (one-hot, label, target encoding), binning. Outlier management (IQR, Z-score). Normalisation (Min-Max, StandardScaler, RobustScaler). Class balancing (SMOTE, under-sampling, class weights). Exploratory analysis with pandas profiling and visualisations. Stratified train/test/validation split.
Supervised algorithms
Linear and polynomial regression, Ridge/Lasso/ElasticNet regularisation. Binary and multiclass logistic regression. Decision trees (CART, split criteria). Ensembles: Random Forest, Bagging. Gradient Boosting: XGBoost, LightGBM, CatBoost (hyperparameters, early stopping). Support Vector Machines (kernels, margins). K-Nearest Neighbors. Metrics: confusion matrix, accuracy, precision, recall, F1-score, AUC-ROC, log-loss, RMSE, MAE, R². Choice of metrics according to business context.
Unsupervised learning and dimensionality reduction
Clustering: K-means (choice of K, elbow method, silhouette score), DBSCAN (eps, min_samples), hierarchical clustering (dendrograms, linkage). Dimensionality reduction: PCA (explained variance, interpretation), t-SNE, UMAP. Anomaly detection: Isolation Forest, One-Class SVM, Local Outlier Factor. Association rules (Apriori, support, confidence). Use cases: customer segmentation, data compression, fraud detection.
Model optimisation and validation
Cross-validation: k-fold, stratified k-fold, leave-one-out. Hyperparameter search: GridSearchCV, RandomizedSearchCV, Optuna, Hyperopt. Regularisation to avoid overfitting. Feature selection: SelectKBest, RFE, feature importance. Learning curves and validation curves. Management of bias-variance tradeoff. Advanced ensemble methods: stacking, blending. Probability calibration.
Deployment and MLOps
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
Is knowledge of Deep Learning required for this certification?
No, this certification focuses on classical Machine Learning (supervised, unsupervised). Deep Learning is covered in higher-level certifications. You must master scikit-learn, XGBoost and traditional algorithms.
Which tools and libraries are assessed?
The exam mainly covers Python with scikit-learn, pandas, NumPy, matplotlib/seaborn. XGBoost and LightGBM are included. Questions focus on practical implementation and choosing appropriate algorithms according to business contexts.
Does the exam involve writing code?
The exam consists of 40 multiple-choice questions, in 60 minutes, online under automated surveillance.
Is this certification recognised by European recruiters?
Yes, PROVA is aligned with the EQF and ESCO frameworks, recognised throughout the EU. The detailed PROVA DNA report is particularly appreciated by technical recruiters.
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.
