Winter School in Data Analytics and Machine Learning
Many firms and organizations have recognized the value of analyzing data based on quantitative tools like regression, machine learning, and deep learning
- for forecasting specific outcomes such as sales or prices (predictive analysis),
- for evaluating the causal impact of specific actions such as offering discounts or running marketing campaigns (causal analysis).
This permits improving the quality of decision making and thus increasing efficiency and competitiveness.
The “Fribourg Winter School in Data Analytics and Machine Learning” provides training in state-of-the-art quantitative tools for predictive and causal analysis. The winter school takes place in hybrid form, implying that participants can attend courses either in class (face-to-face) or online. Please note that the sessions will not be recorded. The one- to three-days-courses cover both introductory and more advanced topics, using the open source software packages “Python”, “R”, "Julia" and “Knime”. “Python”, “R” and "Julia" are among the most popular programming languages in data science and statistics, while “Knime” is a user-friendly, flow-chart based graphical interface that does not require any programming skills.
Among the topics covered in the various courses are
- regression techniques for multivariate statistical analysis;
- machine and deep learning algorithms like lasso, decision trees, random forests, and neural nets;
- text analysis to extract and statistically analyze text information from websites, like sentiments about products.
-
Overview of the courses
Instructor
Course
Software
Level
Date
ECTS
KNIME
introductory (no programming required)
Feb 3
0.5
R
introductory
Feb 4
0.5
R
intermediate
Feb
5-6
1.0
Julia
introductory
Feb 7
0.5
Python
intermediate
Feb
10-11
1.0
Python
advanced
Feb
12-14
1.5
-
Participants
The winter school is open to BA students, MA students, Ph.D. students, and academic researchers (such as post-docs and professors) at the University of Fribourg and at other universities or research institutions, as well as to employees of private companies and the public sector.
-
Teaching modalities
The working language will be English. Courses are held in a spacious lecture hall on the Pérolles campus (Boulevard de Pérolles 90, CH-1700 Fribourg) and can also be attended online. Please note that the sessions will not be recorded.
-
Examination / evaluation
Take home exam: students obtain a dataset with several exercises to solve that need to be resubmitted in order to be graded. Without taking the exam, students can nevertheless obtain a certificate of participation (without grade).
Take home exams to be solved until March 31, 2025.
-
Credits
Successful participation in the courses (and examinations) can be credited with up to 5 ECTS points (if winter schools are recognized by the home university/institution)
-
Course fees
BA, MA, and Ph.D. of the University of Fribourg
BA/MA/PhD students at other universities or academic researchers (e.g. post-docs, professors...) at the University of Fribourg or elsewhere
private companies
and public sector
*Flat rate
for all courses:
CHF 90
Block 1:
KNIME course
(3 Feb)
CHF 220
Block 1:
KNIME course
(3 Feb)
CHF 330
Block 2:
R courses
(4-6 Feb)
CHF 550
Block 2:
R courses
(4-6 Feb)
CHF 880
Block 3:
Julia course
(7 Feb)
CHF 220
Block 3:
Julia course
(7 Feb)
CHF 330
Block 4:
Python courses
(10 -11 Feb)
CHF 410
Block 4:
Python courses
(10 -11 Feb)
CHF 610
Block 5:
(12-14 Feb)
CHF 550
Block 5:
(12-14 Feb)
CHF 880
Block 4 & 5
(10-14 Feb)
CHF 670
Block 4 & 5
(10-14 Feb)
CHF 1030
All courses:
(3-14 Feb)
CHF 1100
All courses:
(3-14 Feb)
CHF 1720
*Please note: Not all courses have to be attended.
-
Payment
Payment is made directly via the online registration form. Please note that the registration is only complete when we have received the registration fee. The deadline for online registration and payment is January 27, 2025.
-
Location
University of Fribourg, Boulevard de Pérolles 90, 1700 Fribourg, Switzerland.
-
Accomodation
Participants must book their accommodations themselves.
Here are a few recommendations: