Prototyping data science products

Objective:

The main objective is to teach students how to transform their ideas and data science knowledge into a product prototype. During the seminar, the students will improve their programming skills in R (or Python, at their choice), learn to apply machine learning techniques to a concrete problem, create a product prototype and run it on the cloud. All participants will receive free credits on the Google Cloud Platform (courtesy of a Google Educational Grant) that they can use to get familiar with the services and cover the cost of running their product prototype.

In the Fall Semester 2023, the seminar will be organised in collaboration with SWISS International Air Lines. With the support of our partners, students will develop the prototype of a route planning tool that leverages state of the art machine learning algorithms. As some confidential information might be exchanged during the seminar, all accepted students will be required to sign a research and a non- disclosure agreement prior to the start of the seminar.

Learning outcome:

The seminar gives an overview of the fundamental steps needed to create a product prototype for a data science web application. Topics include getting familiar with google cloud computing platform, training machine learning algorithms, structuring a project and running it on the cloud. Most services we discuss provide a high-level, user friendly (often graphical) interface. Therefore, no previous knowledge of cloud infrastructure is required.

Syllabus: Prototyping HS23 (PDF, 191 KB)

Instructors:
Dr. Radu Tanase
Debora Costa

Contact:
Radu.tanase@business.uzh.ch

Type:
Seminar

Target audience:
MA students with basic programming and machine learning knowledge, who are interested in turning their ideas into a web application. Assigned to “Wahlpflichtbereich BWL 4”.

Frequency:
Each Fall Semester

AP(ECTS)-points:
3

Language:

English

Course material:
Slides, videos and learning resources will be provided during the seminar

Prerequisites:

Students can choose to program in either R or Python. Therefore, we recommend the following courses:
A non-technical introduction to R (or equivalent knowledge)
OR
A non-technical introduction to Python (or equivalent knowledge).

Recommended prior knowledge:
Good programming knowledge in R or Python. Basic knowledge of machine learning.

Grading:

Online Exercises (30%)
Group Project (60%) - Final Presentations 30.11.2023
Peer evaluation (10%)

Dates and Location:

Location: AND 3.44

Further information:
www.market-research.uzh.ch

Registration:
The number of participants is limited to 20. To apply, please send your application via email to radu.tanase@business.uzh.ch with the subject "Application PDSP HS2023". The application should contain your CV, transcript of records, and a short letter of motivation. The application deadline is Wednesday, September 13th, 2023 at 23:59 CEST. The application results will be communicated on Friday, September 15th.

Note:
This information supports the official information in the electronic university calendar (VVZ – Vorlesungsverzeichnis). In case of doubt, the official information at the VVZ is valid.

Data Camp
This class is supported by DataCamp, the most intuitive learning platform for data science and analytics. Learn any time, anywhere and become an expert in R, Python, SQL, and more. DataCamp’s learn-by-doing methodology combines short expert videos and hands-on-the-keyboard exercises to help learners retain knowledge. DataCamp offers 325+ courses by expert instructors on topics such as importing data, data visualization, and machine learning.