Intern assignment
By | Pawel Roman, Le Viet Duc |
Thesis or intern assignment | Early‑warning prediction of quality deviations using multivariate time‑series machine learning |
Wavin department | Discovery |
Education of candidate | Data Science / Computer Science / Applied Mathematics / Industrial Engineering (Bachelor) |
Description of the assignment
Rather than responding after a quality deviation occurs, it is valuable to detect early signals that indicate a deviation is likely to happen soon.
In this assignment you will build a machine‑learning model that predicts the likelihood of a quality deviation ahead of time using historical time‑series data. You will define an appropriate prediction target, train and evaluate baseline and improved models, and assess performance in terms of lead time and false alarms. The output should be interpretable and suitable for future use in monitoring or alerting applications.
Goal of the assignment
Build and evaluate an early‑warning model that predicts upcoming quality deviations with sufficient lead time.
Additional information
Intern type: Bachelor assignment
Duration: 2 months
Workload: Full‑time (minimum 32 hours/week)
Gross reimbursement per month (full‑time): 400 EUR
About Wavin
Wavin is an innovative solution provider for the building and infrastructure industry globally. With over 60 years’ of expertise, we aim to solve global challenges in water supply, sanitation, climate-resilient cities and building performance. We are committed to building healthy, sustainable environments. Wavin is headquartered in the Netherlands, and has presence in over 25 countries.
Contact:
Le Viet Duc