Predicting with machine learning: from raw data to a validated, explainable model.
Predictive models steer decisions: who gets an offer, where maintenance goes, how much gets ordered. The power lies in the right question, strong features and honest evaluation.
Explainability is not a luxury but a precondition: a model whose predictions nobody understands will not be used — or worse, will be used wrongly.
Building the model was the subject: choosing features, comparing algorithms, tuning hyperparameters. That part has largely been automated away — a language model writes the pipeline faster than you can type it, and usually just as well.
What remains is the hardest part, and it never was the typing: deciding whether the model answers the right question, whether the data covers reality, and whether the error it makes is acceptable to whoever bears it.
You build a predictive model on data from your own organisation — and make it explainable for users.
An HR analyst predicts attrition risk and shows which factors make the difference.
A buyer forecasts demand per product group and lowers stock without lost sales.
An underwriter gets the three main reasons with every score — and can deviate with justification.
You take this module the way you take the whole programme: classes every other week on Friday and Saturday, with a study load of 15–20 hours per week, of which 10–15 hours is self-study. The teaching is a mix of classroom sessions, workplace learning, blended learning and working groups or study teams — taught by lecturers who practise the profession themselves on a daily basis.
You conclude each theme with a professional product or a technical solution addressing a real situation in your own work, which you discuss in an assessment with the lecturer. This way your portfolio grows with real work — and your employer benefits directly.
The format is not new: the teaching approach and the AI modules have been running for three years at the AI Proeflokaal — with business, with government, and across part-time modules and minors. What you meet in class here has already been worn in elsewhere.
After this module you deliver a validated, explainable ML model on your own data, ready for use.
Email or call the programme team — we are happy to think it through with you.