Syllabus

Title
1360 Applications of Data Science: Robotic Process Automation with Machine Learning
Instructors
ao.Univ.Prof. Dr. Johann Mitlöhner
Contact details
Type
PI
Weekly hours
2
Language of instruction
Englisch
Registration
09/01/22 to 09/12/22
Registration via LPIS
Notes to the course
Dates
Day Date Time Room
Wednesday 10/12/22 01:30 PM - 05:30 PM D1.1.078
Wednesday 10/19/22 01:30 PM - 05:30 PM EA.5.040
Wednesday 11/02/22 01:30 PM - 05:30 PM EA.5.040
Wednesday 11/09/22 01:30 PM - 05:30 PM EA.5.040
Wednesday 11/16/22 02:00 PM - 06:00 PM EA.5.040
Wednesday 11/23/22 02:00 PM - 06:00 PM D1.1.074
Contents
  • Introduction to Robotic Process Automation Concepts
  • Introduction to the Robot Framework (https://robotframework.org/)
  • Simple Cases of Process Automation using the Robot Framework
  • Introduction to some basic Machine Learning and Text Mining methods for Process Automation
  • Combining Robot Framework and Machine Learning for Robotic Process Automation
Learning outcomes

  • Acquire a basic understanding of the importance of Robotic Process Automation
  • Learn about business process automation using software robots
  • Understand the integration of the process automation with machine learning
  • Understand the basics of robotic process automation via simple examples

Attendance requirements

At least 80% attendance (physical presence, WU Check-in) is required i.e. 5 out of 6 units.

 

Teaching/learning method(s)

  • Lecture
  • Practical Exercises (homework, not graded but discussed as desired by the participants)
  • Programming project (homework, submitted after final unit and graded)

For the programming project participants select a topic in coordination with the lecturer. The project involves robotic process automation using the robot framework and some very simple machine learning approaches as presented in the lecture. The programming project will be similar in method but not identical in content to the examples presented in the lecture; it solves the conceptual and technical problems posed by a simple scenario and illustrates the usefulness of the approach. As a software project it of course includes documentation.

Since we only use open source software  students can easily install all packages on their own computer. We will use Python, Jupyter Notebook, and a number of other Python packages. If you can run the pip install manager, then you can install everything we need. However, if students prefer not to use their own computer for the exercises and the final project there are lab rooms available where you can work (ground floor of D2 building entrance C, straight ahead).

Python coding will be necessary in the examples and in the final programming project, but everything will be explained in detail and can be accomplished by participants without extensive experience in the Python programming language.

Virtual consultation via Jitsi will be available for participants who face programming obstacles. Screen sharing  usually solves these problems quickly. Just let me know via email if you desire a telco.

Assessment

Short multiple choice quizzes after each unit via Learn 70%

Final individual programming project 30%

Grading: 50% of total points = 4, 62% = 3, 74% = 2, 86% = 1

Prerequisites for participation and waiting lists

Successful conclusion of the course 1 of SBWL Data Science.

Please be aware that, for all courses in this SBWL, registration is only possibly for students who successfully have completed the entry course (Einstieg in die SBWL: Data Science).

Note that for courses within the SBWL "Data Science" we can only accept students enrolled in one of WU's bachelor programmes who qualify for starting an SBWL; particularly, we cannot accept students from other courses and programmes enrolled at WU as 'Mitbeleger' only.
Recommended previous knowledge and skills

Some experience with Python programming will be helpful.

Availability of lecturer(s)

Directly before or after the course or via E-Mail: johann.mitloehner@wu.ac.at

Last edited: 2022-09-06



Back