DAT320 Sequential and Time Series Data Analysis
Credits (ECTS):10
Campus / Online:Taught campus Ås
Teaching language:Engelsk
Course frequency:Yearly
Nominal workload:
Teaching and exam period:The course begins in the autumn parallel. The course has teaching and evaluation in the autumn parallel.
About this course
The course provides a theoretical and practical introduction to handling, processing, and analyzing data with dependence along one axis, such as sequential or time series data. The course focuses on applications from biology, industrial applications, and finance. The following topics will be covered:
- preprocessing of time series data
- stochastic processes and properties
- forecasting of time series data
- anomaly/outlier detection in time series data
- classification/clustering in time series data
The course presents statistical and machine learning approaches. Students will learn to build effective and accurate models that, depending on the application, can contribute to several of UN's sustainability goals, among others 3, 11, 12, 14, 15.
Learning outcome
- Lectures
- Assignments with presentations (paper and pencil, programming)
- Supplementary online material
- Q&A sessions with teaching assistants
- Machine learning / statistics (DAT200 / STAT200)
- Introductory programming course (INF120 or similar)
- Basic calculus and linear algebra (MATH113 / 131 or similar)
- R programming (will be covered in the lecture, but basic knowledge is an advantage)
Combined evaluation (A-F):
- Portfolio evaluation of exercises including presentation during the term count 40% of the final grade.
- Final written exam (3 hours) counts 60% of the final grade.
Portfolio Grading: Letter grades School exam Grading: Letter grades Permitted aids: B1 Calculator handed out, no other aids- An external censor will participate together with the internal censor in designing the portfolio evaluation and the written exam and including evaluation guidelines. The external censor checks the internal censor's assessment of the final exams of a random selection of candidates as a calibration at certain intervals in line with the faculty's guidelines for censoring.
- Any sessions with compulsory attendance will be announced at the start of the course.
- Lectures and presentation: 4h per week
- Exercises: 2h per week
- Science