The aim of the course is to prepare and equip future scientists and executives in the field of Supply Chain Management with the necessary skills of the interdisciplinary field of Data Science. The course will  introduce the broad scientific field of Machine Learning which is a key area of Artificial ntelligence. Emphasis will be placed on developing intelligent applications utilizing Big Data Analytics techniques for better decision-making on practical supply chain issues. Indicatively, Machine Learning algorithms, methods and models (supervised and unsupervised learning) for big data analysis will be presented, such as: regression methods, classification methods, artificial neural networks, support vector machines, deep learning models, clustering algorithms, dimensionality reduction techniques. The application of these will focus on solving practical supply chain issues, including time series analysis for demand forecasting, inventory management, various optimization problems.  The Anaconda distribution will be used with emphasis on the use of the Python programming language, which has a lot of features and is particularly efficient for applications in the field of Data Science. The source code will be written in interactive development environments (IDEs), mainly JupyterLab and Spyder. For the implementation of practical applications, we will make use of key indicative open-source Python packages (libraries) such as Google OR-Tools, H2O, Matplotlib, NumPy, pandas, scikit-learn, SciPy, Seaborn, statsmodels.Key Cloud Services for code repository management platforms and web-based interactive development environments, such as GitHub and Google Colaboratory (Colab) respectively, will be presented. The programming language R will be presented and compared to Python, with emphasis on their applications in the field of Data Science, for modelling and decision-making in supply chain issues. 

• Presentation of the basic principles of Data Science with a focus on Supply Chain Management, 
• Presentation of Anaconda distribution with creation and management of virtual environments, 
• Introduction to Python Programming Language,
• Data Types and Structures,
• Control Structures,
•  File Handling (Input and Output),
• Define and Call Functions,
• Packages (libraries) for Data Manipulation, Analysis, and Visualization,
• Packages (libraries) for Machine Learning,
• Presentation of Supervised and Unsupervised learning,
• Presentation of Machine Learning algorithms, methods and models, such as:

           – Regression Methods,

          – Classification Methods,

          – Artificial Neural Networks,

           – Support Vector Machine

            – Deep Learning Models,

            – Clustering Algorithms,

             – Dimensionality Reduction Techniques.

• Practical applications in time series analysis for demand forecasting,
• Practical applications in inventory management,
• Practical applications in various optimization problems,
•  Presentation of cloud services (GitHub and Google Colab),
• Presentation and comparison of R programming language versus Python on Data Science in supply chain issues.

Suggested Literature:

• Deitel, H. M., & Deitel, P. J. (2021). Εισαγωγή στην Python για τις Επιστήμες Υπολογιστών και Δεδομένων. Εκδότης: Χ. ΓΚΙΟΥΡΔΑ ΣΙΑ ΕΕ. ISBN: 9789605127442.
•  FAWCETT, T., & PROVOST, F. (2019). Η ΕΠΙΣΤΗΜΗ ΤΩΝ ΔΕΔΟΜΕΝΩΝ ΓΙΑ ΕΠΙΧΕΙΡΗΣΕΙΣ. Εκδότης: ΕΚΔΟΣΕΙΣ ΚΛΕΙΔΑΡΙΘΜΟΣ ΕΠΕ. ISBN: 9789604619917.
• Hillier, F. S., Lieberman, G. J., & Διαμαντίδης, Α. (Επιστ. Επιμέλεια) (2021). Εισαγωγή Στην Επιχειρησιακή Έρευνα (11η Έκδοση). Εκδότης: ΕΚΔΟΣΕΙΣ Α. ΤΖΙΟΛΑ & ΥΙΟΙ Α.Ε. ISBN: 9789604189168.
• MATTHES, E. (2020). Η ΓΛΩΣΣΑ ΠΡΟΓΡΑΜΜΑΤΙΣΜΟΥ PYTHON. Εκδότης: ΕΚΔΟΣΕΙΣ ΔΙΣΙΓΜΑ ΙΚΕ.
  ISBN: 9786182020036.
•  Muddana, A. L., & Vinayakam, S. (2024). Python for Data Science. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-52473-8
• Sunil, C., Ανδρουτσόπουλος, Κ., & Μαντάς, Μ. (Επιστ. επιμέλεια). (2020). Διοίκηση Εφοδιαστικής Αλυσίδας, 7η Έκδοση. Εκδότης: ΕΚΔΟΣΕΙΣ Α. ΤΖΙΟΛΑ & ΥΙΟΙ Α.Ε. ISBN: 9789604188758.
• Βλαχάβας, Ι., Κεφαλάς, Π., Βασιλειάδης, Ν., Κόκκορας, Φ., & Σακελλαρίου, Η. (2020). ΤΕΧΝΗΤΗ ΝΟΗΜΟΣΥΝΗ – 4η ΕΚΔΟΣΗ. Εκδότης: ΕΤΑΙΡΕΙΑ ΑΞΙΟΠΟΙΗΣΗΣ ΚΑΙ ΔΙΑΧΕΙΡΙΣΗΣ ΠΕΡΙΟΥΣΙΑΣ ΠΑΝΕΠΙΣΤΗΜΙΟΥ ΜΑΚΕΔΟΝΙΑΣ. ISBN: 9786185196448.
• ΔΙΑΜΑΝΤΑΡΑΣ, Κ., & ΜΠΟΤΣΗΣ, Δ. (2019). ΜΗΧΑΝΙΚΗ ΜΑΘΗΣΗ. Εκδότης: ΕΚΔΟΣΕΙΣ ΚΛΕΙΔΑΡΙΘΜΟΣ ΕΠΕ. ISBN: 9789604619955.

Related academic journals

• Big Data Mining and Analytics, IEEE
• Big Data Research, Elsevier
•  Computers & Industrial Engineering, Elsevier
• Data Mining and Knowledge Discovery, Springer
• Data Science and Engineering, Springer
•  European Journal of Operational Research, Elsevier
•  Expert Systems with Applications, Elsevier
• IEEE Transactions on Knowledge and Data Engineering, IEEE
•  International Journal of Data Science and Analytics, Springer
•  International Journal of Production Economics, Elsevier
• International Journal of Production Research, Taylor & Francis
• Management Science, INFORMS
• Operational Research, Springer

Greek

Lectures, Laboratory Exercises