Course description for 2020/21
Statistical and Machine Learning
FIN5002
Course description for 2020/21
Statistical and Machine Learning
FIN5002
The course provides an introduction to machine learning from a statistical point of view. It provides an overview of new processes and technology, as well as training in specific methods and tools that can be used to analyze large amounts of data, as well as how results can best be communicated to different stakeholders. The course provides a thorough introduction to how to retrieve and process different types of data, as well as statistical methods for analyzing the amount of data in the supervised and unsupervised setting of machine learning. Methods reviewed in the regression and classification context include amongst others regression, decision trees and neural networks. Such methods are best learned through practice, so the course comprises a practical part with the statistical software R for retrieving data, analyzing the amount of data, and communicating and visualizing the results.
It is possible to apply for admission to the course as a single course. There are reservations about the available capacity on the course. The applicant must meet the current admission requirements for the Master of Science in Business or Master of Accounting and Auditing.
Must fulfill the requirements for admission to the two year Master of Science in Business program.
Knowledge
The student:
- Has advanced knowledge of what digitalization and automation means for different industries, witha special focus on finance.
- Has in-depth knowledge of areas in data analysis and statistical methods for carrying out an analysis of data types of different types and sizes, using methods such as for example random Forests.
- Has in-depth knowledge of international research in topics related to the course, such as regression analysis, decision trees and machine learning.
- Have knowledge and practical understanding of data integrity, including data reliability, complete and accurate data transfer, data cleaning and data erasure.
- Can apply knowledge to new areas in data analysis, map data flow into systems and processes relevant to different industries.
- Can analyze professional issues with tools and techniques from the subject's specificity.
Skills
The student:
- Analyze existing models, theories and methods of statistics for large amounts of data using appropriate tools
- Can use relevant tools, methods, and theories for research within the subject's main themes in an independent manner.
- Can analyze and relate critically to various sources of information used in different contexts within automation of work tasks.
- Can conduct, produce and evaluate independent analytical research work under guidance in accordance with research ethical norms.
- Can use analytical and digital tools, such as for example R, Python or Tableu, in practical work, both for data collection, data analysis, and communication of results as well as present results in both written, verbal and graphical terms
- Can write a complete scientific report in one file using a software of own choice
General competence
The student:
- aHve a thorough understanding of the change processes that are happening and expected in the future, as well as analyze relevant issues within the digitization of different industries.
- Communicate comprehensive independent work and master expressions in digitalization, automation and relevance for future tasks, such as presentation of graphical illustrations of variables and changes over time, individuals or both
- Can apply their competence to new areas and issues in business analysis and counseling.
- Can contribute to innovative thinking and innovative solutions to issues related to digitization and automation.
- Can discuss and communicate professional issues with different stakeholders.
- Can evaluate and consider the most appropriate method of digital business analysis for a given industry or data source.
- Can use and easily acquire skills about new digital Tools.
No tuition fees. Costs for semester registration and course literature apply.
Optional
Weekly lectures
The programme is evaluated accirding to the university's quality assurance system.
Composite assessment, grading rule Letter grades
- Written school exam, 4 hours, counts 60/100 of the grade, grading rule Letter grades.
- Assignment - group work, counts 20/100 of the grade, grading rule Letter grades.
- Oral - Presentation, counts 20/100 of the grade, grading rule Letter grades.
We reserve the right to change the assessment method. The correct assessment method is displayed in StudentWeb when registering for the relevant course.
Pen, pencil, ruler, bilingual dictionary and simple calculator.
FIN5000 (Econometrics)