
A career-boosting data science bootcamp
Bratislava — 23-27 January 2023
Target Audience
PhD students who need to handle data, use statistics or build models in their research.
Analysts who want to swing away from Excel and start working with big data, applying machine learning and create eloquent visualisations.
Professionals wanting to learn more about machine learning and statistics.
Format
- Intense 5-days of coding and thinking about data science problems
- Hands-on workshops with real-world datasets and data challenges
- Interactive lectures on important data science concepts
- Group projects with individual support by our expert team
- Python introduction to data handling
- A combination of theoretical and practical workshops
- A day of three specialised streams led by tutors with vast experience in the field
Goals
- Educate about data science
- Provide the necessary skills to handle data
- Raise awareness of strengths and weaknesses of machine learning models
- Cover the important topics often overlooked by online courses
- Advance the research and performance of the attendees by supporting their journey towards data literacy
- Talk about problems that seniors encountered in their workflows
- Teach how to avoid “junior” mistakes in interpretation of analytical results
Program
- Welcome and Opening. Intro to python and data processing (day 1)
- Data Visualisation (day 2)
- Statistics and regression modelling (day 3)
- Machine Learning (day 4)
- Optional streams (day 5)
- Stream 1 – Healthcare analytics and epidemiology
- Stream 2 – Biomedical data analysis and bioinformatics
- Stream 3 – Econometrics and social analytics
1. Day
- Welcome and opening
- Presentation: Data Science
- Intro to Python programming
- Strings handling
- Data importing, cleaning, filtering in Pandas library
- Data storage
- Exercise: Missing values and data aggregation
2. Day
- Data visualisation
- Interactive graphs
- Dashboards
- Geographical plotting
- Presentation: Data communication
- Exercise: Multivariate plots
3. Day
- Intro to Statistical Inference and Hypothesis testing
- Presentation: Causality vs Correlation
- Regression Modelling
- Presentation: Predictive performance measures
- Logistic Regression
- Presentation: Statistics vs Machine Learning
- Exercise: Exploratory data analysis
4. Day
- Intro to Machine Learning
- Supervised Learning (Prediction)
- Model inspection, feature importance, partial dependence
- Unsupervised Learning (Clustering)
- Dimensionality Reduction, Anomaly detection
- Presentation: Interpretability vs complexity
- Exercise: Looking for the best predictive model
5. Day – Choose a specialisation
- Stream 1 – Healthcare analytics and epidemiology
- Case exercise 1: Standardised incidence and prevalence of diseases
- Case exercise 2: Analysing survival rates of patients after surgeries
- Case exercise 3: Regional differences in drug prescriptions
- Stream 2 – Biomedical data analysis and bioinformatics
- Case exercise 1: Visualisation and clustering of high dimensional single cell RNA seq data
- Case exercise 2: Cancer research pipeline: from gene expression to protein-protein interactions to therapeutics
- Case exercise 3: Cross-talk of the microbiome and cancer: Exploring the unknown with the power of data
- Stream 3 – Econometrics and social analytics
- Case exercise 1: Exploring social cohesion – Fresh World Value Survey data
- Case exercise 2: Churn analysis – predicting which clients are going to leave
- Case exercise 3: Political survey analysis
More information
- Start – 23rd of January 2023
- End – 27th of January 2023
- A course day starts at 9:00 and ends at 18:00 with breaks for coffee and lunch.
- Coffee breaks and lunch are all covered in the price.
-
The specialized streams on the fifth day are lectured in parallel, in separate classes.
-
No programming experience is required to attend.
-
We will emphasize data visualization and writing simple clean code during the course.
-
Participants will encounter plenty of data cleaning problems along the exercises.
-
Forums for knowledge and experience exchange, are an essential aspect of our new community.
Required knowledge
Basic quantitative skills
No programming skills needed
Familiarity with computer programming or database structures is a benefit, but not a requirement. Winter School is set up in a way that beginners will learn the basics and do some hands-on experimentation with guidance, while participants with some experience will be able to see best practices, utilise their knowledge and do some additional magic on really cool datasets while consulting with experienced mentors!
Python
Widely considered as one of the best programming languages for beginners, Python is a general purpose language that is currently the best choice for data science and machine learning applications. During the first day, we will walk you through the basics of this language and how to use it to solve data science tasks.
JOIN OUR NEW CROSS-DISCIPLINARY DATA SCIENCE COMMUNITY
Private Sector
Public Sector
Academia
5 days of lectures and workshops by industry leaders
Exercises and mentoring
Carefully prepared curriculum
Presentations from external speakers
Networking opportunities
Knowledge exchange
Membership in the new data science community
Team
We are all passionate about data science in our daily work. This is our journey to share the knowledge and improve Slovak science and policy making.

Imrich Berta
Imrich graduated Applied Mathematics at University of Cambridge and worked on research in machine learning methods for disease prediction at University of Edinburgh. He currently holds the position of Head of Data Science at a healthcare provider company that operates several hospitals. During his career, Imrich mentored several junior analysts and organised coding workshops for students.

Laura Johanesová
Laura is a biomedical scientist currently studying Evolutionary Systems Biology at University of Vienna. With strong focus on R, Linux and Python throughout her studies, she developed interest in biotechnology and works on research in regeneration where programming knowledge is crucial for the interpretation of lab-acquired data. Together with Jakub, she will be teaching the Biomedical stream at the WDS.

Jakub Hantabal
Jakub is a biochemist and bioinformatician collaborating with scientists in the United Kingdom and Slovakia on research of the tumour microenvironment and novel proteins, utilising both data-driven and laboratory methods. Jakub used his bioinformatics skills in a discovery of a novel protein in the parasite liver fluke. Currently, studying Precision Cancer Medicine at University of Oxford.

Ján Dudek
Jan Dudek studied economics and econometrics at Rice University and Oxford University, graduating magna cum laude. He worked at the Ministry of Health (IZP), where he significantly improved the ensuree risk-equalization scheme, as well as implemented an ML pilot for fraud detection in Slovak healthcare (winning a European Commission grant). He now works as a data scientist, focusing on fraud detection and incentive programs for health providers.

Damian Harateh
Damian Harateh graduated with Computer Science from UCL, and Law, Accounting & Finance from University of Kent. Currently, Head of Qanuk AI, a start-up developing AI solutions for eCommerce, CEO of Kodyte, an eCommerce consultancy and a Partnership Manager at an award-winning eCommerce agency, Snowdog. Previously, a Software Engineer at IBM. Damian is in charge of all technological needs of the Winter Data School.
Contact Us

Website
www.winterdataschool.com

Contact
Imrich Berta
+44 7858 115 591
imrich.berta@venturelab.sk

Address