Application of Machine Learning Methods

Wyższa Szkoła Zarządzania i Bankowości w Krakowie działa nieprzerwanie od 1995 roku, łącząc akademicką wiedzę z praktyką. Uczelnia kształci na kierunkach: Informatyka, Informatyka stosowana, Zarządzanie, Finanse i rachunkowość, Logistyka, Marketing cyfrowy, Przedsiębiorczość cyfrowa oraz Komunikacja i psychologia w biznesie. Programy studiów są projektowane z myślą o potrzebach współczesnej gospodarki i współpracy z otoczeniem biznesowym. W ofercie znajdują się także studia podyplomowe oraz kursy rozwijające kompetencje zawodowe. Uczelnia stawia na rozwój praktycznych umiejętności, przedsiębiorczości, innowacyjności oraz kompetencji cenionych na rynku pracy.

Learning Outcomes

The micro-credential certifies that the learner possesses in-depth knowledge, practical skills, and social competencies in designing, training, optimizing, and evaluating machine learning models, with a particular focus on practical applications in the field of data science.

The learner who earned the micro-credential knows and understands:

• machine learning methods (including regression, classification, clustering, neural networks),
• the workings and limitations of popular ML algorithms (e.g., Random Forest, SVM, k-NN),
• key machine learning concepts such as cost function, gradient, overfitting, and underfitting,
• methods for preparing, enriching, and organizing data for ML models,
• principles of experiment planning and model quality evaluation.

The learner is able to:

• construct and train machine learning models for various types of problems,
• select appropriate algorithms and techniques for specific analytical tasks,
• design ML experiments (e.g., cross-validation, hyperparameter optimization),
• analyze model results, compare approaches, and draw conclusions,
• visualize algorithm operations and interpret results.

Estimated Workload

4 ECTS credits

Level (referenced to the Polish Qualifications Framework / European Qualifications Framework – EQF)

PRK7/EQF7

Assessment Method(s)

The micro-credential was granted on the basis of a positive evaluation of a project completed during seminar sessions.

The verification of learning outcomes included mainly:

• the accuracy of data preparation and ML model construction,
• the appropriateness of algorithm selection for the problem being addressed,
• the quality of designed experiments and result analyses,
• the ability to interpret results and draw conclusions,
• independence and responsibility in project execution.

Mode of Delivery

The micro-credential certifies the completion of 100 hours of theoretical classes, practical sessions, and the student's independent work.

Quality Assurance Arrangements Underpinning the Micro-credential

The issuance of the micro-credential is based on a coherent outcomes matrix (knowledge, skills, and social competencies) – content – assessments, their verification, and agreed-upon teaching methods, in accordance with the course syllabus (practical profile) and under the supervision of the course coordinator. The quality of education is ensured by transparent criteria and passing thresholds, systematic evaluation of results, and periodic updates of content and methods based on conclusions from assessments and feedback from internal and external stakeholders.