Course Objective & Scope
Most machine learning projects fail on basics such as a poorly framed problem or data leakage. This programme builds a solid footing in classification, regression and clustering, the bias-variance trade-off, cross-validation and metrics such as accuracy, precision, recall and RMSE.
Participants work end to end in Python, pandas and scikit-learn on a dataset resembling their organisation's own data, and finish with a documented problem definition and a baseline model.
Who Should Attend?
- Software developers moving into machine learning
- Data analysts and BI specialists
- Data engineers joining ML projects
- Prerequisite: basic Python and experience with tabular data
Key Takeaways
- Frame a business problem as a classification, regression or clustering task
- Set up train/validation/test splits without data leakage
- Train and compare baseline models with scikit-learn
- Diagnose overfitting and underfitting using learning curves
- Select and justify an evaluation metric that fits the problem type
Curriculum
ML Problem Framing and Data Preparation
- Supervised vs unsupervised and choosing the target variable
- Exploratory data analysis and missing-value handling with pandas
Regression and Classification Algorithms
- Linear and logistic regression, decision trees, k-NN
- Reproducible training with scikit-learn Pipelines
Clustering and Dimensionality Reduction
- k-means, DBSCAN and interpreting segments
- PCA for visualisation and noise reduction
Model Evaluation and Cross-Validation
- Confusion matrix, precision/recall, ROC-AUC, RMSE
- k-fold cross-validation and data leakage pitfalls
Baseline Project
- End-to-end baseline on data resembling the organisation's case
- Writing up the problem definition and sharing results
Other Courses in This Category
-
Gradient boosting, ensembles and stacking, hyperparameter optimisation with Optuna, imbalanced data, probability calibration and custom loss functions for experienced data scientists building production-grade models.
- Live Course
- 5 modules
-
Takes analysts beyond classic reporting with segmentation, driver analysis, anomaly flagging and simple predictive models in Python, scikit-learn and SHAP, producing analyses that tie insight to business decisions.
- Live Course
- 5 modules
-
Categorical encoding, time and window-based features, target encoding, interaction and text features, feature selection and feature stores: a systematic approach to the step that most improves model performance on tabular data.
- Live Course
- 5 modules
-
Choosing the right metrics, evaluation tied to business KPIs, error analysis, fairness checks and model explanation with SHAP, LIME and PDP, so models can be presented to stakeholders reliably and understandably.
- Live Course
- 5 modules
-
Independent model validation: data and conceptual soundness checks, backtesting, stability (PSI), challenger models, stress tests and findings reporting, producing a validation report aligned with a model risk management framework.
- Live Course
- 5 modules
-
Time series forecasting with ARIMA, ETS, Prophet and LightGBM-based approaches, working hands-on with seasonality, exogenous variables, hierarchical series, backtesting and prediction intervals to build reliable forecasts.
- Live Course
- 5 modules
Get in touch
