Objectives and competences
Students design project plan for data science project. Gather and prepare financial data from publicly available data warehouses. Are able to conduct the project by themselves and appropriately present the results, in the manner ready for a user.
Content (Syllabus outline)
1. Preparation and workflow of data science projects
2. Interpretation of results
3. Preparing and presenting the results for and to users
4. Time validity of performed projects
5. Professional ethics in data science
Learning and teaching methods
discussion; individual study; case studies;
Intended learning outcomes - knowledge and understanding
Upon successful completion of the course, the student will be able to:
1. Identify business needs for data science projects and distinguish as well as evaluate the quality of different data science projects (PILO 2a, 2b).
2. Acquire and appropriately prepare financial data from publicly available data repositories and critically assess completed data science projects (PILO 2c).
3. Analyze complex, incomplete, and conflicting knowledge domains and clearly explain the results of the analysis (PILO 2c, 3a).
4. Independently argue their findings in analytical work on a selected research question or case study (PILO 3b, 4b).
5. Recognize ethical dilemmas and demonstrate professional responsibility in managing risks in data science projects (PILO 4a).
6. Critically evaluate the sustainability and societal impacts of a completed data science project (PILO 4b).
The PILO label (i.e., Programme Intended Learning Outcomes) defines the contribution of each listed intended learning outcome of a course towards achieving the general and/or subject-specific competencies or learning outcomes acquired through the programme.
Intended learning outcomes - transferable/key skills and other attributes
Upon successful completion of the course, the student will be able to:
1. Identify business needs for data science projects and distinguish as well as evaluate the quality of different data science projects (PILO 2a, 2b).
2. Acquire and appropriately prepare financial data from publicly available data repositories and critically assess completed data science projects (PILO 2c).
3. Analyze complex, incomplete, and conflicting knowledge domains and clearly explain the results of the analysis (PILO 2c, 3a).
4. Independently argue their findings in analytical work on a selected research question or case study (PILO 3b, 4b).
5. Recognize ethical dilemmas and demonstrate professional responsibility in managing risks in data science projects (PILO 4a).
6. Critically evaluate the sustainability and societal impacts of a completed data science project (PILO 4b).
The PILO label (i.e., Programme Intended Learning Outcomes) defines the contribution of each listed intended learning outcome of a course towards achieving the general and/or subject-specific competencies or learning outcomes acquired through the programme.
Readings
Hagan, M. T., Demuth, H. B., & Beale, M. (1996). Neural network design. Boston, MA: PWS Publishing Company.
Dodatna literatura / Additional:
Nabor aktualnih člankov s področja podatkovne znanosti./Selection of scientific papers in the area of data science.
Machine Learning Onramp: Machine Learning Onramp | Self-Paced Online Courses - MATLAB & Simulink (mathworks.com)
Machine Learning with MATLAB: Machine Learning with MATLAB | Self-Paced Online Courses - MATLAB & Simulink (mathworks.com)
Deep Learning Onramp: Deep Learning Onramp | Self-Paced Online Courses - MATLAB & Simulink (mathworks.com)
Self-Paced Online Courses: Deep Learning with MATLAB | Self-Paced Online Courses - MATLAB & Simulink (mathworks.com)
Self-Paced Online Courses: Reinforcement Learning Onramp | Self-Paced Online Courses - MATLAB & Simulink (mathworks.com)
Additional information on implementation and assessment Project 100%
Project - writing an individual project and oral presentation
