• The student has basic knowledge of Python is able to program simple scripts.

• The student is able to perform basic data preparation manipulations on a given dataset.

Knowledge Discovery (6 ECTS) is designed to build foundational skills in traditional machine learning and data mining for business applications. The course progresses systematically from core concepts to practical implementation, covering supervised learning (e.g., kNN, Decision Trees, Logistic Regression, Ensemble Methods), unsupervised techniques (e.g,. Clustering, Association Rule Mining), and advanced topics (e.g., SVM, Feature Engineering, SHAP-based interpretability). Students gain essential skills in data preprocessing (using pandas/Colab), model evaluation (e.g., accuracy, precision, recall), and hyperparameter tuning (including cross-validation and automated methods)—all applied directly to real-world business challenges such as customer segmentation and churn prediction. Hands-on labs and a capstone project enable application to real datasets using Python.