Prediction and Forecasting
-
Teacher(s)Siem Jan Koopman
-
Research fieldData Science, Management Science
-
DatesPeriod 3 - Jan 08, 2024 to Mar 01, 2024
-
Course typeField
-
Program yearSecond
-
Credits3
Course description
External participants are invited to register for this course. (PhD) students register here, others register here. More information on course registration and course fees can be found here.
Every decision in finance, business and economics has an impact on the future and therefore it ultimately must depend on forecasts. This course covers all the elementary and introductory knowledge necessary for analysing, modelling, prediction and forecasting time series using basic concepts in statistics and econometrics. The course discusses the main tools for making appropriate predictions and forecasts for a variety of problems: demand for goods, market shares, financial risk, energy prices, and macroeconomic variables such as inflation. Furthermore, it discusses signal extraction and extrapolation methods for high-dimensional data sets.
- Introduction and basic forecasting methods
- Decomposition of time series: trend and seasonal effects
- Exponential smoothing methods
- Box-Jenkins models
- What is a good forecast?
- Kalman filter methods
- Score-driven models
- Signal extraction and extrapolation for many time series.
Course literature
To be made available on Canvas. Book TBA and selected papers.