Data Analytics (Modular Course)

Next edition in summer 2021. Dates to be confirmed.

Course description:

Through this modular course of four weeks, data analytics skills are developed with emphasis put in their different dimensions (see detailed descriptions for each course). The statistical software R, a flexible and efficient language that builds a bridge between software development and data analysis, is the main support for the acquisition of the relevant data analytics skills. Depending on the student background, each week can be taken independently of the other, although for those with little experience, it is recommended to follow the proposed order.

This course is a modular Course:

Module 1 Computing with R (2 weeks)

Dates to be confirmed.

Module 2 Statistical and Machine Learning for Big Data (1 week)

Dates to be confirmed.

Module 3 Time-Based Analytics (1 week)

Dates to be confirmed.


Application: No reference letter needed for this specific course. Please only submit your -1- CV and your -2- letter of motivation.

Tuition Fees:

Final Deadline: 1st April 2020

Module 1 (2 weeks)

Professionals
External Students
Unige Students
no discount
no discount
no discount
2,600 CHF*
2,000 CHF*
1,000 CHF*


Module 2 or 3 alone (1 week)

Professionals
External Students
Unige Students
no discount
no discount
no discount
1,350 CHF*
1,000 CHF*
600 CHF*


Module 2 + Module 3 (2 weeks totally)

Professionals
External Students
Unige Students
10% Discount
10% Discount
10% Discount
2,340 CHF*
1,800 CHF*
1,080 CHF*


Module 1 + Module 2 (3 weeks totally)

Professionals
External Students
Unige Students
10% Discount
10% Discount
10% Discount
3,555 CHF*
2,700 CHF*
1,440 CHF*


Module 1 + Module 2 + Module 3 (4 weeks totally)

Professionals
External Students
Unige Students
15% Discount
15% Discount
15% Discount
4,505 CHF*
3,400 CHF*
1,870 CHF*


*Including 100 CHF non refundable administrative fees


Faculty & Staff:

Program Directors:

  • Prof. Maria-Pia Victoria-Feser, GSEM, University of Geneva
  • Prof. Stephane Guerrier, GSEM, University of Geneva

Instructors:

Prof. Matthew Beckman:

Assistant Research Professor at the Department of Statistics, Penn State University, as well as the Director of Undergraduate Studies. He earned a PhD in Statistics Education from the University of Minnesota where he previously earned his MS in Statistics. Prior to academia, he worked as a Senior Statistician & Senior Biostatistician in the medical device industry for 8 years. His current research interests include statistics education, educational assessment, and industrial statistics.

Prof. Si Konda

Is an assistant professor in Biostatistics at University of Illinois at Chicago (UIC). He has considerable experience in developing and teaching statistical and machine learning courses. He provided multiple two day analytics and machine learning seminars for Society of Actuaries from 2016-2019 and conducted one-day machine learning workshop at Abbott Labs, Chicago, USA in 2019. He is the recent golden apple award winner for excellence in teaching & leadership at UIC. Si Konda was a visiting faculty at University of Waterloo in 2012 and University of California at Santa Barbara from 2013 to 2015. Si Konda has a Ph.D. in Statistics from the Case Western Reserve University in Cleveland, USA.

Prof. Roberto Molinari:

Obtained a Master degree in International Affairs at the LUISS Guido Carli University in Rome, which brought to experiences in the UNECE, ECD and Ernst & Young. He then obtained a PhD in Statistics (University of Geneva) to become Visiting Professor in statistics at the University of California, Santa Barbara (USA) where he taught introductory Statistics and supervised projects in actuarial sciences. After a year as a consultant for international organizations in West Africa, he returned to academia as Lindsay Assistant Professor at Penn State University (USA) where he continues his research and develops courses in non-parametric statistics and time series analysis. His research interests are in robust estimation for time series models, spatial statistics and model selection as well as applied statistics in the fields of economics, finance and medicine.

Week 1: Introduction to Data Computing with R

  • Become proficient with tools and workflow (R programming language, RStudio development environment, RMarkdown, Git/GitHub source control, Shiny)
  • Introduction to data wrangling using tidyverse tools
  • Achieve proficiency with layered graphs & data visualization
  • Advanced data visualization using ggplot2
  • R for “big data” and complementary tools (e.g., python, C++)

Week 2: R Programming for Data Science

  • Tidy data and iteration using tidyverse: function definition, vectorized operations (e.g., dplyr::do and apply family), iteration (e.g., mosaic::do), non-standard data intake (e.g., web scraping & other sources)
  • Statistical modeling for exploration, inference, and prediction
  • Supervised learning: classification and regression modeling (e.g., decision trees, random forests, naive Bayes, neural networks), regularization, ensemble methods, model evaluation.
  • Unsupervised learning: clustering, dimension reduction
  • Text data in R (regular expressions, ingesting text, analyzing textual data)
  • Interactive graphics and app development (e.g., Shiny, Plot.ly, ggvis)

Olga, Switzerland, R-programming for Data Science Summer School 2019

"Having a management background, I didn’t have any previous knowledge of programming and the Summer School in R-Programming for Data Science at the Université de Genève represented an enriching experience.

The professor was able to introduce the class very well to this statistical software and at the end of the week, with the precious help of the teaching assistants, I was able to solve some real-life problems, coming from the field of statistics and finance. The interdisciplinarity was actually one of the main strengths of the course, showing how R can be tailored to different usages. For me, the presentation of RMarkdown was extremely useful, allowing to create and use data in an easy and quick way, and I have appreciated a lot the introduction to Shiny Web Applications.

In addition, the background of the class was extremely varied, from business analytics to biology, and this represented another remarkable aspect, along with the international environment of both the city and the university. Taking part in it required for sure an academic effort but it was absolutely worth it and gave me the willingness to deepen what I learnt!"