Chair of Information Management

Master Seminar "Machine Learning in the Context of Digital Transformation" - M.Sc.





General Information



  • Module: Machine Learning in the Context of Digital Transformation
  • UniVZ: 800146
  • Cycle: Every winter term
  • Credits: 12 ECTS
  • Courses of study: Master WI, Master Ufü
  • Type of teaching and learning: Seminar (2 SWS), groups of 2 students, maximum of 20 participants
  • Each seminar paper will be prepared by a group of two students. First pre-registered, first served.
  • Examination: Attendance at seminar dates, handing in a seminar paper, and holding a presentation. Presentation (approx. 30 minutes) with written seminar paper elaboration (max. 8000 words)
  • Language: English
  • Lecturer: Dr. Andre Hanelt
  • Contact: Sromona Chatterjee, Schahin Tofangchi
  • Office Hours in Göttingen: In case of organisational issues, please contact Sromona Chatterjee
  • For information on a certain topic, please contact the corresponding tutor directly.





Winter Term 2017/2018 Dates



  • Pre-Registration period begins on 1st Septembre and is carried out via email to Sromona Chatterjee. Registration mails prior to this date will not be considered for the pre-registration process. Please note: It is mandatory to pre-register and topic selection will be done in a first pre-registered, first served manner.
  • Registration at the Examination Office is mandatory. The registration in Flexnow will be open from 25th Octobre to 15th Novembre 2017.
  • Kick-off meeting: 18th Octobre 2017, 10.00 am - 05.00 pm, Großer Seminarraum (SUB)
  • Handing in the presentation: 30th January 2018, by 12.00 pm, via email to Sromona Chatterjee
  • Date of presentation: 31st January 2018, 09.00 am - 03.00 pm, Großer Seminarraum (SUB)
  • Handing in the paper: 15th February 2018, by 12.00 pm, Room 3.104 at Humboldtallee 3


  • Topics


    1) Autonomous Vehicles: Predicting Energy Consumption and Balancing Efficiency and Comfortability (supervisor contact: Schahin Tofangchi)
    2) Building and Personalising Shared Smart Homes (supervisor contact: Schahin Tofangchi)
    3) Computational Grounded Theory: Inductive Theory Generation from Qualitative Data (supervisor contact: Schahin Tofangchi)
    4) Profiling: Modelling User Behaviour Based on State-Action Pairs (supervisor contact: Schahin Tofangchi)
    5) Real-time Tracking of Ecosystem Members Based on Financial Indicators (supervisor contact: Schahin Tofangchi)
    6) Predicting Firm Performance from their Similarity to Market Leaders and Startups (supervisor contact: Schahin Tofangchi)
    7) Modelling Semantics of Documents and Measuring their Similarities (supervisor contact: Schahin Tofangchi)
    8) Consumer Household Psychometrics: Predicting Purchasing Behavior Using Graphical Neural Networks (supervisor contact: Schahin Tofangchi)
    9) Exploring the Financial Impact of Business Strategy Specificity (supervisor contact: Dr. Andre Hanelt)
    10) Scaling E-Car Sharing Rental data (supervisor contact: Alfred Benedikt Brendel)
    11) Predicting Service and Product Announcements via Social Media Data (supervisor contact: Alfred Benedikt Brendel)
    12) Predicting the Energy Demand and Travel Distance of an Electric Vehicle within an e-Car-Sharing System (supervisor contact: Alfred Benedikt Brendel)
    13) Recurrent Neural Network and Object Recognition (supervisor contact: Sromona Chatterjee)
    14) Patch Recognition on Roads and Machine Learning (supervisor contact: Sromona Chatterjee)
    15) Object Recognition: TBA (supervisor contact: Sromona Chatterjee)



    Learning objectives


    This seminar is concerned with relevant topics in Machine Learning and Big Data Analytics. Within your group you deal with a challenging topic related to (un-)supervised learning algorithms and their applications, automated image/text analysis, reinforcement learning, memory learning, distributed/real-time data analytics, and statistical learning theory in general. On the basis of highly independent, self-driven research, you prepare your topic, practice to present your academic solutions in front of an audience, and handle their upcoming questions. Your seminar project may deal with theoretical questions or practical implementations of Machine Learning and Big Data systems. This seminar offers you the opportunity to lay the foundation for a subsequent Master's thesis.

    Pay attention to the guidelines for seminar theses.