Universität Osnabrück
Seminar: Time Series Analysis and Forecasting - Details
You are not logged into Stud.IP.

General information

Course number 8.3415
Semester WS 2019/20
Current number of participants 98
Home institute LE Cognitive Science
Courses type Seminar in category Offizielle Lehrveranstaltungen
First date Fri , 01.11.2019 16:00 - 18:00, Room: 93/E31
Art der Durchführung Onlineveranstaltung
Hauptsächliche Kursbelegung keine Angabe
SWS 2
Sprache Englisch
Contact Hours 2
ECTS points 4

Course location / Course dates

93/E31 Friday: 16:00 - 18:00, weekly (from 01/11/19) (14x)
15/323-324 Friday. 28.02.20 12:00 - 16:00

Module assignments

Comment/Description

Time series data is sequential data that is usually observed with a fixed interval between the observations (e.g. daily, weekly, monthly, etc.). Examples include predicting sales or workload and forecasting the weather or natural disasters. As opposed to common classification and regression tasks, it is usually not reasonable to assume that observations in a time series are independent.

It is often reasonable to assume that the data-generating process is composed of a systematic (consisting of components like level, trend and seasonality) and a non-systematic component (noise). In this course, we will discuss statistical approaches that attempt to reconstruct the data-generating process and machine learning methods that simply focus on patterns in data. Statistical approaches are often more transparent and statistical tools can be used in order to compute confidence intervals and to test hypotheses. Furthermore, they can be used to remove trend and seasonality components from the observations, which often improves the performance of machine learning approaches. On the other hand, machine learning approaches can be a valuable tool when the assumptions of model-based approaches are violated. They are also more flexible in incorporating external information like special events (e.g. holidays or large social events that can affect sales and traffic conditions). Both approaches can be combined in order to improve the overall performance.

The seminar will consist of lectures introducing basic analysis and forecasting tools, programming and analysis tasks and discussions.

Prerequisites: basic knowledge of Python (basic programming and SciPy stack) and Statistics (random variables, descriptive statistics, regression).