Dear all,

I mentioned the new double degree program with the University of Twente "Business Information Systems and Data Science" in a previous post. Since the application deadline is drawing nearer, I would like to bring it to your attention.

The program is brand new and focuses on Data Science. Graduates of the program will receive two Master degrees, one from us and the other from the University of Twente. About half of your subjects will be taught in Münster and the other half in Enschede, the Netherlands.

All Master of Information Systems, students can take part in the program, even in case you already completed subjects here.  For more information, have a look here and here. In case your questions cannot be answer there, please don't hesitate to contact either Stefan Schellhammer or Olga Lunina.

To plan elective courses inSummer term 2021, a preliminary survey is conducted.

If you are willing to  participate to a seminar or project seminar in summer term , please join this survey in the Learnweb:

https://www.uni-muenster.de/LearnWeb/learnweb2/mod/feedback/view.php?id=1828876

The survey is now open and will be closed on 2020/11/30 8:00 a.m.

An application phase will follow during the last two weeks of lecture time and will be announced separately in the Coordinator's Blog. 

Note that participation in this survey is a neccessary condition. That means: if during application phase a larger number of applications shows up compared to the numbers given by this survey and, due to this underestimation of capacity there are too few places in offered seminars/project seminars,  then students with an application but without participation in the survey risk to be disregarded. On the other side during application phase, applications of students who have participated in this survey will usually be considered.

Yours sincerely

Ingolf Terveer

am 24.11., 15 Uhr, veranstalten das Institut für Angewandte Informatik den dritten Jobhub IT - die Karrieremesse der Uni Münster.

Die Veranstaltung richtet sich an Studierende mit Informatik-Bezug, die sich für Praktika, Stellen als Werkstudent*innen, Abschlussarbeiten bei Praxispartnern und natürlich Dauerstellen nach erlangtem Abschluss interessieren oder einfach nur IT-bezogene Firmen aus der Region kennen lernen wollen.

Doktorand*innen (kurz) vor dem Abschluss sind natürlich auch willkommen.

Aufgrund der Corona-Pandemie wird die Veranstaltung diesmal als Zoom-Meeting stattfinden. (mehr Infos hier)

Wie üblich werden sich die beteiligten Firmen zunächst in einer gemeinsamen Sitzung der Reihe nach kurz vorstellen. Danach besteht die Gelegenheit, die interessierenden Firmen in jeweils eigenen Zoom-Räumen zu besuchen.

Liebe WI-Studierende im 3. Studienjahr,

im dritten Studienjahr stehen Wahlpflichtmodule, d.h. zwei Vertiefungsmodule (VM) und ein Projektseminar (PS)  auf dem Plan (zur Teilnahme daran ist erforderlich, dass sämtliche Leistungen des 1. Studienjahres erfolgreich absolviert sind). Um das Lehrangebot an VM/PS  imSommersemester 2021 planen zu können und auch das grundsätzliche Interesse am Vertiefungsmodul BWL auszuloten, wollen wir in diesem Semester wieder auf eine Umfrage zurückgreifen.

Sie finden die Bedarfsumfrage Umfrage unter dem Link

https://www.uni-muenster.de/LearnWeb/learnweb2/mod/feedback/view.php?id=1828837

Bitte nehmen Sie sich 5 Minuten Zeit, die wenigen Fragen zu beantworten. Die Umfrage ist ab heute 12:00 Uhr  bis  Donnerstag 26. November 2020, 08:00 Uhr geöffnet.

Ein letztes Wort zum Übergang vom Bachelor in den Master: Eine vergleichbare Bedarfsumfrage/Bewerbungsphase wird es auch für den  Master "Information Systems" geben. Bachelor-Studierende, die im nächsten Semester in den Master wechseln, können wir jetzt noch nicht in die dort angebotenen Seminare und Projektseminare einteilen, eine Teilnahme an Bedarfs- und Bewerbungsphase im Master ist nicht möglich. Seminare und Projektseminare im Master liegen laut Studienverlaufsplan auch erst im 2. und höheren Mastersemester. Das Lehrangebot an Vorlesungen im ersten Mastersemester ist ausreichend hoch, so dass Sie Ihren Stundenplan im ersten Mastersemester auch  ohne Sem/PS füllen können.

Mit freundlichen Grüßen

Ingolf Terveer

Dear students,

As you might know, the ERCIS has a long-standing tradition of having Lunchtime Talks during the semester. Usually, they take place at Leo 18, but due to some specific circumstances, they will be held virtual this year. On November 17^th, we will have the first talk – if you are interested, please register with the link below, and you will receive the Zoom link today by 11.45, afterwards in due time before.

https://www.ercis.org/research/ercis-lunchtime-seminar

About the talk:

We are pleased to invite you to the first talk in the series, presented by Dr. Johannes Kriebel. Johannes is an assistant professor at the Finance Center Münster. His work focuses on topics related to credit risk and machine learning as well as digital transformation in financial service providers.

Johannes will present a project on the use of natural language processing to predict credit risk from user-generated text data on peer-to-peer lending platforms. Please find an abstract, as well as further details for logging in, below.

We will open the waiting room at 12.00 (UTC+1) and open doors to the “seminar room” at 12.15. As usual, we will have time for discussions afterwards until roughly 13.00.

Abstract

Digital technologies produce vast amounts of unstructured data that can be stored and accessed by traditional banks and fintech companies. Existing literature on the topic indicates that certain aspects of this unstructured data can be valuable for decision-making regarding the acceptance and pricing of credit contracts. Both practitioners and academics are interested in understanding the value of this information and how to exploit it for credit risk predictions. We employ deep learning techniques to extract credit-relevant information from user-generated text on the peer-to-peer platform Lending Club. Our results confirm that even short pieces of user-generated text can improve credit default predictions significantly and generate substantial additional profit for lenders. We benchmark four deep neural network architectures and more traditional approaches (machine learning and rule-based text characteristics) to retrieving credit-relevant information from text. Average embedding neural networks, convolutional neural networks, and recurrent neural networks achieve similar prediction quality while outperforming convolutional recurrent neural networks. Deep learning models achieve better results than traditional approaches in almost all cases; in traditional approaches, spelling mistakes are particularly informative.